diff --git "a/sf_log.txt" "b/sf_log.txt"
new file mode 100644--- /dev/null
+++ "b/sf_log.txt"
@@ -0,0 +1,3146 @@
+[2025-04-03 12:58:39,177][06091] Saving configuration to /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json...
+[2025-04-03 12:58:39,178][06091] Rollout worker 0 uses device cpu
+[2025-04-03 12:58:39,179][06091] Rollout worker 1 uses device cpu
+[2025-04-03 12:58:39,179][06091] Rollout worker 2 uses device cpu
+[2025-04-03 12:58:39,180][06091] Rollout worker 3 uses device cpu
+[2025-04-03 12:58:39,181][06091] Rollout worker 4 uses device cpu
+[2025-04-03 12:58:39,181][06091] Rollout worker 5 uses device cpu
+[2025-04-03 12:58:39,181][06091] Rollout worker 6 uses device cpu
+[2025-04-03 12:58:39,182][06091] Rollout worker 7 uses device cpu
+[2025-04-03 12:58:39,228][06091] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 12:58:39,229][06091] InferenceWorker_p0-w0: min num requests: 2
+[2025-04-03 12:58:39,244][06091] Starting all processes...
+[2025-04-03 12:58:39,245][06091] Starting process learner_proc0
+[2025-04-03 12:58:39,294][06091] Starting all processes...
+[2025-04-03 12:58:39,301][06091] Starting process inference_proc0-0
+[2025-04-03 12:58:39,301][06091] Starting process rollout_proc0
+[2025-04-03 12:58:39,302][06091] Starting process rollout_proc1
+[2025-04-03 12:58:39,302][06091] Starting process rollout_proc2
+[2025-04-03 12:58:39,302][06091] Starting process rollout_proc3
+[2025-04-03 12:58:39,303][06091] Starting process rollout_proc4
+[2025-04-03 12:58:39,368][06091] Starting process rollout_proc5
+[2025-04-03 12:58:39,368][06091] Starting process rollout_proc6
+[2025-04-03 12:58:39,369][06091] Starting process rollout_proc7
+[2025-04-03 12:58:41,026][06289] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 12:58:41,026][06289] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-04-03 12:58:41,105][06311] Worker 7 uses CPU cores [28, 29, 30, 31]
+[2025-04-03 12:58:41,125][06308] Worker 0 uses CPU cores [0, 1, 2, 3]
+[2025-04-03 12:58:41,128][06312] Worker 5 uses CPU cores [20, 21, 22, 23]
+[2025-04-03 12:58:41,137][06289] Num visible devices: 1
+[2025-04-03 12:58:41,170][06306] Worker 1 uses CPU cores [4, 5, 6, 7]
+[2025-04-03 12:58:41,178][06310] Worker 3 uses CPU cores [12, 13, 14, 15]
+[2025-04-03 12:58:41,189][06289] Starting seed is not provided
+[2025-04-03 12:58:41,189][06289] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 12:58:41,189][06289] Initializing actor-critic model on device cuda:0
+[2025-04-03 12:58:41,189][06289] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 12:58:41,190][06289] RunningMeanStd input shape: (1,)
+[2025-04-03 12:58:41,199][06305] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 12:58:41,199][06305] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-04-03 12:58:41,199][06289] ConvEncoder: input_channels=3
+[2025-04-03 12:58:41,200][06309] Worker 4 uses CPU cores [16, 17, 18, 19]
+[2025-04-03 12:58:41,206][06307] Worker 2 uses CPU cores [8, 9, 10, 11]
+[2025-04-03 12:58:41,228][06305] Num visible devices: 1
+[2025-04-03 12:58:41,289][06313] Worker 6 uses CPU cores [24, 25, 26, 27]
+[2025-04-03 12:58:41,354][06289] Conv encoder output size: 512
+[2025-04-03 12:58:41,354][06289] Policy head output size: 512
+[2025-04-03 12:58:41,377][06289] Created Actor Critic model with architecture:
+[2025-04-03 12:58:41,377][06289] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2025-04-03 12:58:42,665][06289] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-04-03 12:58:43,489][06289] No checkpoints found
+[2025-04-03 12:58:43,489][06289] Did not load from checkpoint, starting from scratch!
+[2025-04-03 12:58:43,489][06289] Initialized policy 0 weights for model version 0
+[2025-04-03 12:58:43,495][06289] LearnerWorker_p0 finished initialization!
+[2025-04-03 12:58:43,495][06289] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 12:58:43,659][06305] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 12:58:43,660][06305] RunningMeanStd input shape: (1,)
+[2025-04-03 12:58:43,667][06305] ConvEncoder: input_channels=3
+[2025-04-03 12:58:43,723][06305] Conv encoder output size: 512
+[2025-04-03 12:58:43,723][06305] Policy head output size: 512
+[2025-04-03 12:58:43,750][06091] Inference worker 0-0 is ready!
+[2025-04-03 12:58:43,750][06091] All inference workers are ready! Signal rollout workers to start!
+[2025-04-03 12:58:43,783][06306] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,783][06308] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,783][06311] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,784][06309] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,784][06310] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,784][06312] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,784][06307] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,792][06313] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 12:58:43,944][06311] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:43,945][06308] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:43,946][06310] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:43,946][06307] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:43,959][06309] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:43,965][06306] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:44,059][06310] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,069][06308] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,077][06307] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,094][06306] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,105][06309] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,112][06313] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:44,212][06311] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,220][06310] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,231][06312] Decorrelating experience for 0 frames...
+[2025-04-03 12:58:44,242][06307] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,253][06313] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,344][06312] Decorrelating experience for 32 frames...
+[2025-04-03 12:58:44,361][06309] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,374][06311] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,384][06310] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,397][06307] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,404][06306] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,487][06308] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,515][06312] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,527][06313] Decorrelating experience for 64 frames...
+[2025-04-03 12:58:44,538][06311] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,565][06306] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,631][06309] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,656][06308] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,690][06313] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:44,778][06312] Decorrelating experience for 96 frames...
+[2025-04-03 12:58:45,612][06289] Signal inference workers to stop experience collection...
+[2025-04-03 12:58:45,615][06305] InferenceWorker_p0-w0: stopping experience collection
+[2025-04-03 12:58:46,498][06091] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-04-03 12:58:46,499][06091] Avg episode reward: [(0, '1.703')]
+[2025-04-03 12:58:47,163][06289] Signal inference workers to resume experience collection...
+[2025-04-03 12:58:47,163][06305] InferenceWorker_p0-w0: resuming experience collection
+[2025-04-03 12:58:48,875][06305] Updated weights for policy 0, policy_version 10 (0.0109)
+[2025-04-03 12:58:50,546][06305] Updated weights for policy 0, policy_version 20 (0.0007)
+[2025-04-03 12:58:51,498][06091] Fps is (10 sec: 20480.0, 60 sec: 20480.0, 300 sec: 20480.0). Total num frames: 102400. Throughput: 0: 3253.6. Samples: 16268. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 12:58:51,499][06091] Avg episode reward: [(0, '4.381')]
+[2025-04-03 12:58:51,507][06289] Saving new best policy, reward=4.381!
+[2025-04-03 12:58:52,159][06305] Updated weights for policy 0, policy_version 30 (0.0009)
+[2025-04-03 12:58:53,834][06305] Updated weights for policy 0, policy_version 40 (0.0007)
+[2025-04-03 12:58:55,512][06305] Updated weights for policy 0, policy_version 50 (0.0008)
+[2025-04-03 12:58:56,498][06091] Fps is (10 sec: 22937.7, 60 sec: 22937.7, 300 sec: 22937.7). Total num frames: 229376. Throughput: 0: 5340.6. Samples: 53406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 12:58:56,499][06091] Avg episode reward: [(0, '4.408')]
+[2025-04-03 12:58:56,503][06289] Saving new best policy, reward=4.408!
+[2025-04-03 12:58:57,144][06305] Updated weights for policy 0, policy_version 60 (0.0007)
+[2025-04-03 12:58:58,768][06305] Updated weights for policy 0, policy_version 70 (0.0008)
+[2025-04-03 12:58:59,224][06091] Heartbeat connected on Batcher_0
+[2025-04-03 12:58:59,232][06091] Heartbeat connected on RolloutWorker_w0
+[2025-04-03 12:58:59,234][06091] Heartbeat connected on RolloutWorker_w1
+[2025-04-03 12:58:59,235][06091] Heartbeat connected on InferenceWorker_p0-w0
+[2025-04-03 12:58:59,237][06091] Heartbeat connected on RolloutWorker_w2
+[2025-04-03 12:58:59,238][06091] Heartbeat connected on RolloutWorker_w3
+[2025-04-03 12:58:59,239][06091] Heartbeat connected on RolloutWorker_w4
+[2025-04-03 12:58:59,242][06091] Heartbeat connected on RolloutWorker_w5
+[2025-04-03 12:58:59,243][06091] Heartbeat connected on RolloutWorker_w6
+[2025-04-03 12:58:59,244][06091] Heartbeat connected on LearnerWorker_p0
+[2025-04-03 12:58:59,246][06091] Heartbeat connected on RolloutWorker_w7
+[2025-04-03 12:59:00,400][06305] Updated weights for policy 0, policy_version 80 (0.0007)
+[2025-04-03 12:59:01,498][06091] Fps is (10 sec: 24985.7, 60 sec: 23483.8, 300 sec: 23483.8). Total num frames: 352256. Throughput: 0: 4810.0. Samples: 72150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2025-04-03 12:59:01,499][06091] Avg episode reward: [(0, '4.384')]
+[2025-04-03 12:59:02,063][06305] Updated weights for policy 0, policy_version 90 (0.0007)
+[2025-04-03 12:59:03,702][06305] Updated weights for policy 0, policy_version 100 (0.0007)
+[2025-04-03 12:59:05,321][06305] Updated weights for policy 0, policy_version 110 (0.0008)
+[2025-04-03 12:59:06,498][06091] Fps is (10 sec: 24985.6, 60 sec: 23961.7, 300 sec: 23961.7). Total num frames: 479232. Throughput: 0: 5489.0. Samples: 109780. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 12:59:06,499][06091] Avg episode reward: [(0, '4.251')]
+[2025-04-03 12:59:06,975][06305] Updated weights for policy 0, policy_version 120 (0.0008)
+[2025-04-03 12:59:08,563][06305] Updated weights for policy 0, policy_version 130 (0.0009)
+[2025-04-03 12:59:10,190][06305] Updated weights for policy 0, policy_version 140 (0.0007)
+[2025-04-03 12:59:11,498][06091] Fps is (10 sec: 25395.3, 60 sec: 24248.4, 300 sec: 24248.4). Total num frames: 606208. Throughput: 0: 5906.8. Samples: 147670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 12:59:11,499][06091] Avg episode reward: [(0, '4.333')]
+[2025-04-03 12:59:11,827][06305] Updated weights for policy 0, policy_version 150 (0.0008)
+[2025-04-03 12:59:13,543][06305] Updated weights for policy 0, policy_version 160 (0.0008)
+[2025-04-03 12:59:15,151][06305] Updated weights for policy 0, policy_version 170 (0.0007)
+[2025-04-03 12:59:16,498][06091] Fps is (10 sec: 24575.9, 60 sec: 24166.4, 300 sec: 24166.4). Total num frames: 724992. Throughput: 0: 5531.5. Samples: 165946. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 12:59:16,499][06091] Avg episode reward: [(0, '4.368')]
+[2025-04-03 12:59:16,925][06305] Updated weights for policy 0, policy_version 180 (0.0008)
+[2025-04-03 12:59:18,750][06305] Updated weights for policy 0, policy_version 190 (0.0009)
+[2025-04-03 12:59:20,571][06305] Updated weights for policy 0, policy_version 200 (0.0009)
+[2025-04-03 12:59:21,498][06091] Fps is (10 sec: 23346.3, 60 sec: 23990.6, 300 sec: 23990.6). Total num frames: 839680. Throughput: 0: 5743.5. Samples: 201024. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 12:59:21,499][06091] Avg episode reward: [(0, '4.540')]
+[2025-04-03 12:59:21,500][06289] Saving new best policy, reward=4.540!
+[2025-04-03 12:59:22,377][06305] Updated weights for policy 0, policy_version 210 (0.0007)
+[2025-04-03 12:59:24,164][06305] Updated weights for policy 0, policy_version 220 (0.0008)
+[2025-04-03 12:59:25,941][06305] Updated weights for policy 0, policy_version 230 (0.0009)
+[2025-04-03 12:59:26,498][06091] Fps is (10 sec: 22936.9, 60 sec: 23859.0, 300 sec: 23859.0). Total num frames: 954368. Throughput: 0: 5881.5. Samples: 235260. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 12:59:26,500][06091] Avg episode reward: [(0, '4.339')]
+[2025-04-03 12:59:27,772][06305] Updated weights for policy 0, policy_version 240 (0.0008)
+[2025-04-03 12:59:29,635][06305] Updated weights for policy 0, policy_version 250 (0.0009)
+[2025-04-03 12:59:31,498][06091] Fps is (10 sec: 22119.2, 60 sec: 23574.8, 300 sec: 23574.8). Total num frames: 1060864. Throughput: 0: 5594.7. Samples: 251760. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 12:59:31,499][06091] Avg episode reward: [(0, '4.280')]
+[2025-04-03 12:59:31,512][06305] Updated weights for policy 0, policy_version 260 (0.0008)
+[2025-04-03 12:59:33,283][06305] Updated weights for policy 0, policy_version 270 (0.0007)
+[2025-04-03 12:59:35,131][06305] Updated weights for policy 0, policy_version 280 (0.0008)
+[2025-04-03 12:59:36,498][06091] Fps is (10 sec: 22118.8, 60 sec: 23511.0, 300 sec: 23511.0). Total num frames: 1175552. Throughput: 0: 5979.3. Samples: 285336. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 12:59:36,499][06091] Avg episode reward: [(0, '4.752')]
+[2025-04-03 12:59:36,504][06289] Saving new best policy, reward=4.752!
+[2025-04-03 12:59:37,027][06305] Updated weights for policy 0, policy_version 290 (0.0009)
+[2025-04-03 12:59:38,915][06305] Updated weights for policy 0, policy_version 300 (0.0008)
+[2025-04-03 12:59:40,737][06305] Updated weights for policy 0, policy_version 310 (0.0009)
+[2025-04-03 12:59:41,498][06091] Fps is (10 sec: 22528.0, 60 sec: 23384.5, 300 sec: 23384.5). Total num frames: 1286144. Throughput: 0: 5886.7. Samples: 318306. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 12:59:41,499][06091] Avg episode reward: [(0, '4.565')]
+[2025-04-03 12:59:42,551][06305] Updated weights for policy 0, policy_version 320 (0.0008)
+[2025-04-03 12:59:44,470][06305] Updated weights for policy 0, policy_version 330 (0.0009)
+[2025-04-03 12:59:46,291][06305] Updated weights for policy 0, policy_version 340 (0.0009)
+[2025-04-03 12:59:46,498][06091] Fps is (10 sec: 22118.4, 60 sec: 23278.9, 300 sec: 23278.9). Total num frames: 1396736. Throughput: 0: 5836.2. Samples: 334780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 12:59:46,499][06091] Avg episode reward: [(0, '4.379')]
+[2025-04-03 12:59:48,108][06305] Updated weights for policy 0, policy_version 350 (0.0008)
+[2025-04-03 12:59:49,938][06305] Updated weights for policy 0, policy_version 360 (0.0009)
+[2025-04-03 12:59:51,498][06091] Fps is (10 sec: 22118.3, 60 sec: 23415.5, 300 sec: 23189.7). Total num frames: 1507328. Throughput: 0: 5742.3. Samples: 368182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2025-04-03 12:59:51,499][06091] Avg episode reward: [(0, '4.469')]
+[2025-04-03 12:59:51,747][06305] Updated weights for policy 0, policy_version 370 (0.0009)
+[2025-04-03 12:59:53,661][06305] Updated weights for policy 0, policy_version 380 (0.0008)
+[2025-04-03 12:59:55,454][06305] Updated weights for policy 0, policy_version 390 (0.0010)
+[2025-04-03 12:59:56,498][06091] Fps is (10 sec: 22118.4, 60 sec: 23142.4, 300 sec: 23113.1). Total num frames: 1617920. Throughput: 0: 5643.2. Samples: 401614. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 12:59:56,499][06091] Avg episode reward: [(0, '4.233')]
+[2025-04-03 12:59:57,351][06305] Updated weights for policy 0, policy_version 400 (0.0008)
+[2025-04-03 12:59:59,250][06305] Updated weights for policy 0, policy_version 410 (0.0007)
+[2025-04-03 13:00:01,128][06305] Updated weights for policy 0, policy_version 420 (0.0009)
+[2025-04-03 13:00:01,498][06091] Fps is (10 sec: 21708.7, 60 sec: 22869.3, 300 sec: 22992.2). Total num frames: 1724416. Throughput: 0: 5594.1. Samples: 417682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-04-03 13:00:01,499][06091] Avg episode reward: [(0, '4.423')]
+[2025-04-03 13:00:03,047][06305] Updated weights for policy 0, policy_version 430 (0.0008)
+[2025-04-03 13:00:04,911][06305] Updated weights for policy 0, policy_version 440 (0.0008)
+[2025-04-03 13:00:06,498][06091] Fps is (10 sec: 21709.1, 60 sec: 22596.3, 300 sec: 22937.6). Total num frames: 1835008. Throughput: 0: 5542.6. Samples: 450440. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:00:06,499][06091] Avg episode reward: [(0, '4.298')]
+[2025-04-03 13:00:06,706][06305] Updated weights for policy 0, policy_version 450 (0.0008)
+[2025-04-03 13:00:08,643][06305] Updated weights for policy 0, policy_version 460 (0.0009)
+[2025-04-03 13:00:10,585][06305] Updated weights for policy 0, policy_version 470 (0.0010)
+[2025-04-03 13:00:11,498][06091] Fps is (10 sec: 21709.0, 60 sec: 22254.9, 300 sec: 22841.2). Total num frames: 1941504. Throughput: 0: 5504.4. Samples: 482954. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:00:11,499][06091] Avg episode reward: [(0, '4.468')]
+[2025-04-03 13:00:12,523][06305] Updated weights for policy 0, policy_version 480 (0.0008)
+[2025-04-03 13:00:14,382][06305] Updated weights for policy 0, policy_version 490 (0.0008)
+[2025-04-03 13:00:16,273][06305] Updated weights for policy 0, policy_version 500 (0.0010)
+[2025-04-03 13:00:16,498][06091] Fps is (10 sec: 21708.5, 60 sec: 22118.4, 300 sec: 22801.0). Total num frames: 2052096. Throughput: 0: 5500.4. Samples: 499280. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 13:00:16,499][06091] Avg episode reward: [(0, '4.185')]
+[2025-04-03 13:00:18,233][06305] Updated weights for policy 0, policy_version 510 (0.0009)
+[2025-04-03 13:00:20,017][06305] Updated weights for policy 0, policy_version 520 (0.0009)
+[2025-04-03 13:00:21,498][06091] Fps is (10 sec: 22117.9, 60 sec: 22050.2, 300 sec: 22765.1). Total num frames: 2162688. Throughput: 0: 5474.3. Samples: 531682. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:00:21,499][06091] Avg episode reward: [(0, '4.417')]
+[2025-04-03 13:00:21,771][06305] Updated weights for policy 0, policy_version 530 (0.0008)
+[2025-04-03 13:00:23,551][06305] Updated weights for policy 0, policy_version 540 (0.0008)
+[2025-04-03 13:00:25,288][06305] Updated weights for policy 0, policy_version 550 (0.0008)
+[2025-04-03 13:00:26,498][06091] Fps is (10 sec: 22938.0, 60 sec: 22118.5, 300 sec: 22814.7). Total num frames: 2281472. Throughput: 0: 5519.1. Samples: 566664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 13:00:26,499][06091] Avg episode reward: [(0, '4.463')]
+[2025-04-03 13:00:27,043][06305] Updated weights for policy 0, policy_version 560 (0.0009)
+[2025-04-03 13:00:28,792][06305] Updated weights for policy 0, policy_version 570 (0.0009)
+[2025-04-03 13:00:30,539][06305] Updated weights for policy 0, policy_version 580 (0.0007)
+[2025-04-03 13:00:31,498][06091] Fps is (10 sec: 23347.8, 60 sec: 22254.9, 300 sec: 22820.6). Total num frames: 2396160. Throughput: 0: 5545.0. Samples: 584304. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:00:31,499][06091] Avg episode reward: [(0, '4.245')]
+[2025-04-03 13:00:32,286][06305] Updated weights for policy 0, policy_version 590 (0.0008)
+[2025-04-03 13:00:33,999][06305] Updated weights for policy 0, policy_version 600 (0.0009)
+[2025-04-03 13:00:35,768][06305] Updated weights for policy 0, policy_version 610 (0.0008)
+[2025-04-03 13:00:36,498][06091] Fps is (10 sec: 23346.7, 60 sec: 22323.2, 300 sec: 22863.1). Total num frames: 2514944. Throughput: 0: 5585.4. Samples: 619524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2025-04-03 13:00:36,499][06091] Avg episode reward: [(0, '4.194')]
+[2025-04-03 13:00:36,503][06289] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000614_2514944.pth...
+[2025-04-03 13:00:37,552][06305] Updated weights for policy 0, policy_version 620 (0.0010)
+[2025-04-03 13:00:39,407][06305] Updated weights for policy 0, policy_version 630 (0.0008)
+[2025-04-03 13:00:41,239][06305] Updated weights for policy 0, policy_version 640 (0.0007)
+[2025-04-03 13:00:41,498][06091] Fps is (10 sec: 22937.3, 60 sec: 22323.1, 300 sec: 22830.7). Total num frames: 2625536. Throughput: 0: 5592.7. Samples: 653286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 13:00:41,499][06091] Avg episode reward: [(0, '4.372')]
+[2025-04-03 13:00:43,139][06305] Updated weights for policy 0, policy_version 650 (0.0009)
+[2025-04-03 13:00:45,166][06305] Updated weights for policy 0, policy_version 660 (0.0007)
+[2025-04-03 13:00:46,498][06091] Fps is (10 sec: 21299.6, 60 sec: 22186.7, 300 sec: 22732.8). Total num frames: 2727936. Throughput: 0: 5592.3. Samples: 669334. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 13:00:46,499][06091] Avg episode reward: [(0, '4.479')]
+[2025-04-03 13:00:47,131][06305] Updated weights for policy 0, policy_version 670 (0.0008)
+[2025-04-03 13:00:48,954][06305] Updated weights for policy 0, policy_version 680 (0.0008)
+[2025-04-03 13:00:50,763][06305] Updated weights for policy 0, policy_version 690 (0.0008)
+[2025-04-03 13:00:51,498][06091] Fps is (10 sec: 21709.1, 60 sec: 22255.0, 300 sec: 22741.0). Total num frames: 2842624. Throughput: 0: 5580.9. Samples: 701582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2025-04-03 13:00:51,499][06091] Avg episode reward: [(0, '4.408')]
+[2025-04-03 13:00:52,461][06305] Updated weights for policy 0, policy_version 700 (0.0008)
+[2025-04-03 13:00:54,205][06305] Updated weights for policy 0, policy_version 710 (0.0008)
+[2025-04-03 13:00:55,905][06305] Updated weights for policy 0, policy_version 720 (0.0009)
+[2025-04-03 13:00:56,498][06091] Fps is (10 sec: 23346.9, 60 sec: 22391.5, 300 sec: 22780.0). Total num frames: 2961408. Throughput: 0: 5645.8. Samples: 737016. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:00:56,499][06091] Avg episode reward: [(0, '4.417')]
+[2025-04-03 13:00:57,636][06305] Updated weights for policy 0, policy_version 730 (0.0007)
+[2025-04-03 13:00:59,395][06305] Updated weights for policy 0, policy_version 740 (0.0009)
+[2025-04-03 13:01:01,139][06305] Updated weights for policy 0, policy_version 750 (0.0008)
+[2025-04-03 13:01:01,498][06091] Fps is (10 sec: 23756.9, 60 sec: 22596.3, 300 sec: 22816.3). Total num frames: 3080192. Throughput: 0: 5676.8. Samples: 754736. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:01:01,499][06091] Avg episode reward: [(0, '4.226')]
+[2025-04-03 13:01:02,867][06305] Updated weights for policy 0, policy_version 760 (0.0007)
+[2025-04-03 13:01:04,606][06305] Updated weights for policy 0, policy_version 770 (0.0009)
+[2025-04-03 13:01:06,314][06305] Updated weights for policy 0, policy_version 780 (0.0008)
+[2025-04-03 13:01:06,498][06091] Fps is (10 sec: 23347.5, 60 sec: 22664.5, 300 sec: 22820.6). Total num frames: 3194880. Throughput: 0: 5746.2. Samples: 790258. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 13:01:06,499][06091] Avg episode reward: [(0, '4.308')]
+[2025-04-03 13:01:08,054][06305] Updated weights for policy 0, policy_version 790 (0.0009)
+[2025-04-03 13:01:09,803][06305] Updated weights for policy 0, policy_version 800 (0.0008)
+[2025-04-03 13:01:11,497][06305] Updated weights for policy 0, policy_version 810 (0.0007)
+[2025-04-03 13:01:11,498][06091] Fps is (10 sec: 23755.3, 60 sec: 22937.4, 300 sec: 22881.0). Total num frames: 3317760. Throughput: 0: 5758.6. Samples: 825806. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 13:01:11,499][06091] Avg episode reward: [(0, '4.286')]
+[2025-04-03 13:01:13,245][06305] Updated weights for policy 0, policy_version 820 (0.0008)
+[2025-04-03 13:01:14,970][06305] Updated weights for policy 0, policy_version 830 (0.0009)
+[2025-04-03 13:01:16,498][06091] Fps is (10 sec: 24166.4, 60 sec: 23074.2, 300 sec: 22910.3). Total num frames: 3436544. Throughput: 0: 5760.8. Samples: 843540. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:01:16,499][06091] Avg episode reward: [(0, '4.286')]
+[2025-04-03 13:01:16,670][06305] Updated weights for policy 0, policy_version 840 (0.0007)
+[2025-04-03 13:01:18,406][06305] Updated weights for policy 0, policy_version 850 (0.0008)
+[2025-04-03 13:01:20,146][06305] Updated weights for policy 0, policy_version 860 (0.0008)
+[2025-04-03 13:01:21,498][06091] Fps is (10 sec: 23348.6, 60 sec: 23142.5, 300 sec: 22911.2). Total num frames: 3551232. Throughput: 0: 5768.5. Samples: 879104. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:01:21,499][06091] Avg episode reward: [(0, '4.500')]
+[2025-04-03 13:01:21,926][06305] Updated weights for policy 0, policy_version 870 (0.0009)
+[2025-04-03 13:01:23,646][06305] Updated weights for policy 0, policy_version 880 (0.0008)
+[2025-04-03 13:01:25,373][06305] Updated weights for policy 0, policy_version 890 (0.0008)
+[2025-04-03 13:01:26,498][06091] Fps is (10 sec: 23346.9, 60 sec: 23142.3, 300 sec: 22937.6). Total num frames: 3670016. Throughput: 0: 5803.4. Samples: 914440. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:01:26,499][06091] Avg episode reward: [(0, '4.486')]
+[2025-04-03 13:01:27,118][06305] Updated weights for policy 0, policy_version 900 (0.0009)
+[2025-04-03 13:01:28,855][06305] Updated weights for policy 0, policy_version 910 (0.0010)
+[2025-04-03 13:01:30,618][06305] Updated weights for policy 0, policy_version 920 (0.0008)
+[2025-04-03 13:01:31,498][06091] Fps is (10 sec: 23756.7, 60 sec: 23210.7, 300 sec: 22962.4). Total num frames: 3788800. Throughput: 0: 5835.9. Samples: 931950. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2025-04-03 13:01:31,499][06091] Avg episode reward: [(0, '4.368')]
+[2025-04-03 13:01:32,335][06305] Updated weights for policy 0, policy_version 930 (0.0008)
+[2025-04-03 13:01:34,091][06305] Updated weights for policy 0, policy_version 940 (0.0008)
+[2025-04-03 13:01:35,859][06305] Updated weights for policy 0, policy_version 950 (0.0011)
+[2025-04-03 13:01:36,498][06091] Fps is (10 sec: 23347.2, 60 sec: 23142.4, 300 sec: 22961.7). Total num frames: 3903488. Throughput: 0: 5904.4. Samples: 967282. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 13:01:36,499][06091] Avg episode reward: [(0, '4.594')]
+[2025-04-03 13:01:37,610][06305] Updated weights for policy 0, policy_version 960 (0.0009)
+[2025-04-03 13:01:39,359][06305] Updated weights for policy 0, policy_version 970 (0.0009)
+[2025-04-03 13:01:40,751][06289] Stopping Batcher_0...
+[2025-04-03 13:01:40,752][06289] Loop batcher_evt_loop terminating...
+[2025-04-03 13:01:40,752][06289] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-04-03 13:01:40,763][06091] Component Batcher_0 stopped!
+[2025-04-03 13:01:40,774][06305] Weights refcount: 2 0
+[2025-04-03 13:01:40,776][06305] Stopping InferenceWorker_p0-w0...
+[2025-04-03 13:01:40,776][06305] Loop inference_proc0-0_evt_loop terminating...
+[2025-04-03 13:01:40,777][06091] Component InferenceWorker_p0-w0 stopped!
+[2025-04-03 13:01:40,796][06310] Stopping RolloutWorker_w3...
+[2025-04-03 13:01:40,797][06310] Loop rollout_proc3_evt_loop terminating...
+[2025-04-03 13:01:40,797][06307] Stopping RolloutWorker_w2...
+[2025-04-03 13:01:40,797][06307] Loop rollout_proc2_evt_loop terminating...
+[2025-04-03 13:01:40,797][06311] Stopping RolloutWorker_w7...
+[2025-04-03 13:01:40,796][06091] Component RolloutWorker_w3 stopped!
+[2025-04-03 13:01:40,798][06311] Loop rollout_proc7_evt_loop terminating...
+[2025-04-03 13:01:40,799][06306] Stopping RolloutWorker_w1...
+[2025-04-03 13:01:40,799][06306] Loop rollout_proc1_evt_loop terminating...
+[2025-04-03 13:01:40,799][06091] Component RolloutWorker_w2 stopped!
+[2025-04-03 13:01:40,799][06312] Stopping RolloutWorker_w5...
+[2025-04-03 13:01:40,800][06312] Loop rollout_proc5_evt_loop terminating...
+[2025-04-03 13:01:40,800][06309] Stopping RolloutWorker_w4...
+[2025-04-03 13:01:40,800][06313] Stopping RolloutWorker_w6...
+[2025-04-03 13:01:40,801][06309] Loop rollout_proc4_evt_loop terminating...
+[2025-04-03 13:01:40,801][06313] Loop rollout_proc6_evt_loop terminating...
+[2025-04-03 13:01:40,801][06308] Stopping RolloutWorker_w0...
+[2025-04-03 13:01:40,801][06091] Component RolloutWorker_w7 stopped!
+[2025-04-03 13:01:40,801][06308] Loop rollout_proc0_evt_loop terminating...
+[2025-04-03 13:01:40,802][06091] Component RolloutWorker_w1 stopped!
+[2025-04-03 13:01:40,803][06091] Component RolloutWorker_w5 stopped!
+[2025-04-03 13:01:40,804][06289] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-04-03 13:01:40,803][06091] Component RolloutWorker_w4 stopped!
+[2025-04-03 13:01:40,804][06091] Component RolloutWorker_w6 stopped!
+[2025-04-03 13:01:40,805][06091] Component RolloutWorker_w0 stopped!
+[2025-04-03 13:01:40,859][06289] Stopping LearnerWorker_p0...
+[2025-04-03 13:01:40,860][06289] Loop learner_proc0_evt_loop terminating...
+[2025-04-03 13:01:40,860][06091] Component LearnerWorker_p0 stopped!
+[2025-04-03 13:01:40,861][06091] Waiting for process learner_proc0 to stop...
+[2025-04-03 13:01:41,581][06091] Waiting for process inference_proc0-0 to join...
+[2025-04-03 13:01:41,582][06091] Waiting for process rollout_proc0 to join...
+[2025-04-03 13:01:41,583][06091] Waiting for process rollout_proc1 to join...
+[2025-04-03 13:01:41,584][06091] Waiting for process rollout_proc2 to join...
+[2025-04-03 13:01:41,585][06091] Waiting for process rollout_proc3 to join...
+[2025-04-03 13:01:41,585][06091] Waiting for process rollout_proc4 to join...
+[2025-04-03 13:01:41,586][06091] Waiting for process rollout_proc5 to join...
+[2025-04-03 13:01:41,588][06091] Waiting for process rollout_proc6 to join...
+[2025-04-03 13:01:41,588][06091] Waiting for process rollout_proc7 to join...
+[2025-04-03 13:01:41,590][06091] Batcher 0 profile tree view:
+batching: 9.3441, releasing_batches: 0.0235
+[2025-04-03 13:01:41,590][06091] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 1.9597
+update_model: 2.3457
+  weight_update: 0.0009
+one_step: 0.0025
+  handle_policy_step: 165.2921
+    deserialize: 4.3999, stack: 0.7375, obs_to_device_normalize: 37.6141, forward: 67.2376, send_messages: 13.0023
+    prepare_outputs: 37.2628
+      to_cpu: 31.3631
+[2025-04-03 13:01:41,591][06091] Learner 0 profile tree view:
+misc: 0.0033, prepare_batch: 12.9575
+train: 28.6743
+  epoch_init: 0.0032, minibatch_init: 0.0048, losses_postprocess: 0.3237, kl_divergence: 0.3482, after_optimizer: 12.3464
+  calculate_losses: 10.3783
+    losses_init: 0.0017, forward_head: 0.7664, bptt_initial: 7.3432, tail: 0.3870, advantages_returns: 0.1074, losses: 0.9804
+    bptt: 0.6815
+      bptt_forward_core: 0.6508
+  update: 5.0071
+    clip: 0.5673
+[2025-04-03 13:01:41,591][06091] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0899, enqueue_policy_requests: 4.6554, env_step: 102.2854, overhead: 4.1498, complete_rollouts: 0.1812
+save_policy_outputs: 5.6012
+  split_output_tensors: 1.9711
+[2025-04-03 13:01:41,592][06091] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0966, enqueue_policy_requests: 4.6806, env_step: 102.2623, overhead: 4.2935, complete_rollouts: 0.1814
+save_policy_outputs: 5.6495
+  split_output_tensors: 1.9855
+[2025-04-03 13:01:41,593][06091] Loop Runner_EvtLoop terminating...
+[2025-04-03 13:01:41,593][06091] Runner profile tree view:
+main_loop: 182.3491
+[2025-04-03 13:01:41,594][06091] Collected {0: 4005888}, FPS: 21968.2
+[2025-04-03 13:03:23,570][06091] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 13:03:23,571][06091] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 13:03:23,572][06091] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 13:03:23,572][06091] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 13:03:23,572][06091] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:03:23,573][06091] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 13:03:23,573][06091] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:03:23,574][06091] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 13:03:23,574][06091] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-04-03 13:03:23,575][06091] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-04-03 13:03:23,575][06091] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 13:03:23,576][06091] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 13:03:23,576][06091] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 13:03:23,577][06091] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 13:03:23,577][06091] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 13:03:23,588][06091] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:03:23,590][06091] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:03:23,592][06091] RunningMeanStd input shape: (1,)
+[2025-04-03 13:03:23,607][06091] ConvEncoder: input_channels=3
+[2025-04-03 13:03:23,702][06091] Conv encoder output size: 512
+[2025-04-03 13:03:23,703][06091] Policy head output size: 512
+[2025-04-03 13:03:24,286][06091] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-04-03 13:03:24,740][06091] Num frames 100...
+[2025-04-03 13:03:24,825][06091] Num frames 200...
+[2025-04-03 13:03:24,929][06091] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
+[2025-04-03 13:03:24,930][06091] Avg episode reward: 2.560, avg true_objective: 2.560
+[2025-04-03 13:03:24,976][06091] Num frames 300...
+[2025-04-03 13:03:25,067][06091] Num frames 400...
+[2025-04-03 13:03:25,163][06091] Num frames 500...
+[2025-04-03 13:03:25,256][06091] Num frames 600...
+[2025-04-03 13:03:25,350][06091] Num frames 700...
+[2025-04-03 13:03:25,406][06091] Avg episode rewards: #0: 4.020, true rewards: #0: 3.520
+[2025-04-03 13:03:25,407][06091] Avg episode reward: 4.020, avg true_objective: 3.520
+[2025-04-03 13:03:25,500][06091] Num frames 800...
+[2025-04-03 13:03:25,590][06091] Num frames 900...
+[2025-04-03 13:03:25,684][06091] Num frames 1000...
+[2025-04-03 13:03:25,774][06091] Num frames 1100...
+[2025-04-03 13:03:25,873][06091] Avg episode rewards: #0: 4.507, true rewards: #0: 3.840
+[2025-04-03 13:03:25,874][06091] Avg episode reward: 4.507, avg true_objective: 3.840
+[2025-04-03 13:03:25,919][06091] Num frames 1200...
+[2025-04-03 13:03:26,008][06091] Num frames 1300...
+[2025-04-03 13:03:26,103][06091] Num frames 1400...
+[2025-04-03 13:03:26,198][06091] Num frames 1500...
+[2025-04-03 13:03:26,288][06091] Avg episode rewards: #0: 4.340, true rewards: #0: 3.840
+[2025-04-03 13:03:26,289][06091] Avg episode reward: 4.340, avg true_objective: 3.840
+[2025-04-03 13:03:26,352][06091] Num frames 1600...
+[2025-04-03 13:03:26,438][06091] Num frames 1700...
+[2025-04-03 13:03:26,526][06091] Num frames 1800...
+[2025-04-03 13:03:26,615][06091] Num frames 1900...
+[2025-04-03 13:03:26,702][06091] Num frames 2000...
+[2025-04-03 13:03:26,796][06091] Num frames 2100...
+[2025-04-03 13:03:26,893][06091] Avg episode rewards: #0: 5.288, true rewards: #0: 4.288
+[2025-04-03 13:03:26,894][06091] Avg episode reward: 5.288, avg true_objective: 4.288
+[2025-04-03 13:03:26,952][06091] Num frames 2200...
+[2025-04-03 13:03:27,043][06091] Num frames 2300...
+[2025-04-03 13:03:27,131][06091] Num frames 2400...
+[2025-04-03 13:03:27,222][06091] Num frames 2500...
+[2025-04-03 13:03:27,303][06091] Avg episode rewards: #0: 5.047, true rewards: #0: 4.213
+[2025-04-03 13:03:27,305][06091] Avg episode reward: 5.047, avg true_objective: 4.213
+[2025-04-03 13:03:27,382][06091] Num frames 2600...
+[2025-04-03 13:03:27,480][06091] Num frames 2700...
+[2025-04-03 13:03:27,584][06091] Num frames 2800...
+[2025-04-03 13:03:27,677][06091] Num frames 2900...
+[2025-04-03 13:03:27,774][06091] Avg episode rewards: #0: 5.063, true rewards: #0: 4.206
+[2025-04-03 13:03:27,775][06091] Avg episode reward: 5.063, avg true_objective: 4.206
+[2025-04-03 13:03:27,836][06091] Num frames 3000...
+[2025-04-03 13:03:27,935][06091] Num frames 3100...
+[2025-04-03 13:03:28,030][06091] Num frames 3200...
+[2025-04-03 13:03:28,123][06091] Num frames 3300...
+[2025-04-03 13:03:28,201][06091] Avg episode rewards: #0: 4.910, true rewards: #0: 4.160
+[2025-04-03 13:03:28,203][06091] Avg episode reward: 4.910, avg true_objective: 4.160
+[2025-04-03 13:03:28,280][06091] Num frames 3400...
+[2025-04-03 13:03:28,367][06091] Num frames 3500...
+[2025-04-03 13:03:28,452][06091] Num frames 3600...
+[2025-04-03 13:03:28,539][06091] Num frames 3700...
+[2025-04-03 13:03:28,602][06091] Avg episode rewards: #0: 4.791, true rewards: #0: 4.124
+[2025-04-03 13:03:28,605][06091] Avg episode reward: 4.791, avg true_objective: 4.124
+[2025-04-03 13:03:28,691][06091] Num frames 3800...
+[2025-04-03 13:03:28,779][06091] Num frames 3900...
+[2025-04-03 13:03:28,864][06091] Num frames 4000...
+[2025-04-03 13:03:28,952][06091] Num frames 4100...
+[2025-04-03 13:03:29,031][06091] Avg episode rewards: #0: 4.828, true rewards: #0: 4.128
+[2025-04-03 13:03:29,033][06091] Avg episode reward: 4.828, avg true_objective: 4.128
+[2025-04-03 13:03:33,142][06091] Replay video saved to /home/haricot/dev/rl-unit8/train_dir/default_experiment/replay.mp4!
+[2025-04-03 13:23:52,900][12851] Saving configuration to /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json...
+[2025-04-03 13:23:52,901][12851] Rollout worker 0 uses device cpu
+[2025-04-03 13:23:52,902][12851] Rollout worker 1 uses device cpu
+[2025-04-03 13:23:52,902][12851] Rollout worker 2 uses device cpu
+[2025-04-03 13:23:52,903][12851] Rollout worker 3 uses device cpu
+[2025-04-03 13:23:52,904][12851] Rollout worker 4 uses device cpu
+[2025-04-03 13:23:52,904][12851] Rollout worker 5 uses device cpu
+[2025-04-03 13:23:52,905][12851] Rollout worker 6 uses device cpu
+[2025-04-03 13:23:52,905][12851] Rollout worker 7 uses device cpu
+[2025-04-03 13:23:52,968][12851] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:23:52,969][12851] InferenceWorker_p0-w0: min num requests: 2
+[2025-04-03 13:23:52,983][12851] Starting all processes...
+[2025-04-03 13:23:52,984][12851] Starting process learner_proc0
+[2025-04-03 13:23:53,033][12851] Starting all processes...
+[2025-04-03 13:23:53,039][12851] Starting process inference_proc0-0
+[2025-04-03 13:23:53,040][12851] Starting process rollout_proc0
+[2025-04-03 13:23:53,040][12851] Starting process rollout_proc1
+[2025-04-03 13:23:53,040][12851] Starting process rollout_proc2
+[2025-04-03 13:23:53,041][12851] Starting process rollout_proc3
+[2025-04-03 13:23:53,041][12851] Starting process rollout_proc4
+[2025-04-03 13:23:53,041][12851] Starting process rollout_proc5
+[2025-04-03 13:23:53,041][12851] Starting process rollout_proc6
+[2025-04-03 13:23:53,042][12851] Starting process rollout_proc7
+[2025-04-03 13:23:54,749][13260] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:23:54,749][13260] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-04-03 13:23:54,761][13275] Worker 2 uses CPU cores [8, 9, 10, 11]
+[2025-04-03 13:23:54,762][13274] Worker 0 uses CPU cores [0, 1, 2, 3]
+[2025-04-03 13:23:54,804][13281] Worker 6 uses CPU cores [24, 25, 26, 27]
+[2025-04-03 13:23:54,808][13279] Worker 4 uses CPU cores [16, 17, 18, 19]
+[2025-04-03 13:23:54,822][13260] Num visible devices: 1
+[2025-04-03 13:23:54,823][13276] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:23:54,823][13276] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-04-03 13:23:54,859][13276] Num visible devices: 1
+[2025-04-03 13:23:54,897][13260] Starting seed is not provided
+[2025-04-03 13:23:54,897][13260] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:23:54,897][13260] Initializing actor-critic model on device cuda:0
+[2025-04-03 13:23:54,897][13260] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:23:54,899][13260] RunningMeanStd input shape: (1,)
+[2025-04-03 13:23:54,906][13273] Worker 1 uses CPU cores [4, 5, 6, 7]
+[2025-04-03 13:23:54,908][13260] ConvEncoder: input_channels=3
+[2025-04-03 13:23:54,911][13278] Worker 5 uses CPU cores [20, 21, 22, 23]
+[2025-04-03 13:23:54,936][13280] Worker 7 uses CPU cores [28, 29, 30, 31]
+[2025-04-03 13:23:54,954][13277] Worker 3 uses CPU cores [12, 13, 14, 15]
+[2025-04-03 13:23:55,029][13260] Conv encoder output size: 512
+[2025-04-03 13:23:55,029][13260] Policy head output size: 512
+[2025-04-03 13:23:55,050][13260] Created Actor Critic model with architecture:
+[2025-04-03 13:23:55,050][13260] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2025-04-03 13:23:55,559][13260] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-04-03 13:23:56,389][13260] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2025-04-03 13:23:56,425][13260] Loading model from checkpoint
+[2025-04-03 13:23:56,427][13260] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2025-04-03 13:23:56,427][13260] Initialized policy 0 weights for model version 978
+[2025-04-03 13:23:56,431][13260] LearnerWorker_p0 finished initialization!
+[2025-04-03 13:23:56,431][13260] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:23:56,583][13276] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:23:56,584][13276] RunningMeanStd input shape: (1,)
+[2025-04-03 13:23:56,592][13276] ConvEncoder: input_channels=3
+[2025-04-03 13:23:56,650][13276] Conv encoder output size: 512
+[2025-04-03 13:23:56,651][13276] Policy head output size: 512
+[2025-04-03 13:23:56,679][12851] Inference worker 0-0 is ready!
+[2025-04-03 13:23:56,680][12851] All inference workers are ready! Signal rollout workers to start!
+[2025-04-03 13:23:56,702][13280] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,703][13275] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,703][13278] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,703][13281] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,704][13273] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,704][13274] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,705][13277] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,707][13279] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:23:56,992][13274] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:56,992][13275] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:56,992][13273] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:56,992][13280] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:56,992][13278] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:57,109][13275] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,119][13278] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,131][13280] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,143][13273] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,155][13277] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:57,163][13274] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,262][13281] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:57,271][13277] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,284][13278] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,301][13273] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,319][13274] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,398][13280] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,427][13275] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,427][13279] Decorrelating experience for 0 frames...
+[2025-04-03 13:23:57,444][13277] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,452][13278] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,477][13274] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,547][13279] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,556][13273] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,586][13275] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,601][13277] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,637][13281] Decorrelating experience for 32 frames...
+[2025-04-03 13:23:57,712][13279] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,753][13280] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,801][13281] Decorrelating experience for 64 frames...
+[2025-04-03 13:23:57,865][13279] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:57,962][13281] Decorrelating experience for 96 frames...
+[2025-04-03 13:23:58,522][13260] Signal inference workers to stop experience collection...
+[2025-04-03 13:23:58,526][13276] InferenceWorker_p0-w0: stopping experience collection
+[2025-04-03 13:23:59,757][13260] Signal inference workers to resume experience collection...
+[2025-04-03 13:23:59,758][13276] InferenceWorker_p0-w0: resuming experience collection
+[2025-04-03 13:23:59,759][13260] Stopping Batcher_0...
+[2025-04-03 13:23:59,759][13260] Loop batcher_evt_loop terminating...
+[2025-04-03 13:23:59,771][13276] Weights refcount: 2 0
+[2025-04-03 13:23:59,774][13276] Stopping InferenceWorker_p0-w0...
+[2025-04-03 13:23:59,774][13276] Loop inference_proc0-0_evt_loop terminating...
+[2025-04-03 13:23:59,774][12851] Component Batcher_0 stopped!
+[2025-04-03 13:23:59,776][12851] Component InferenceWorker_p0-w0 stopped!
+[2025-04-03 13:23:59,784][13274] Stopping RolloutWorker_w0...
+[2025-04-03 13:23:59,785][13274] Loop rollout_proc0_evt_loop terminating...
+[2025-04-03 13:23:59,785][13280] Stopping RolloutWorker_w7...
+[2025-04-03 13:23:59,786][13280] Loop rollout_proc7_evt_loop terminating...
+[2025-04-03 13:23:59,785][12851] Component RolloutWorker_w0 stopped!
+[2025-04-03 13:23:59,787][12851] Component RolloutWorker_w7 stopped!
+[2025-04-03 13:23:59,788][13275] Stopping RolloutWorker_w2...
+[2025-04-03 13:23:59,788][13275] Loop rollout_proc2_evt_loop terminating...
+[2025-04-03 13:23:59,789][13278] Stopping RolloutWorker_w5...
+[2025-04-03 13:23:59,788][12851] Component RolloutWorker_w2 stopped!
+[2025-04-03 13:23:59,789][13278] Loop rollout_proc5_evt_loop terminating...
+[2025-04-03 13:23:59,790][12851] Component RolloutWorker_w5 stopped!
+[2025-04-03 13:23:59,790][13281] Stopping RolloutWorker_w6...
+[2025-04-03 13:23:59,791][13281] Loop rollout_proc6_evt_loop terminating...
+[2025-04-03 13:23:59,791][12851] Component RolloutWorker_w6 stopped!
+[2025-04-03 13:23:59,792][13273] Stopping RolloutWorker_w1...
+[2025-04-03 13:23:59,793][13273] Loop rollout_proc1_evt_loop terminating...
+[2025-04-03 13:23:59,792][12851] Component RolloutWorker_w1 stopped!
+[2025-04-03 13:23:59,793][13279] Stopping RolloutWorker_w4...
+[2025-04-03 13:23:59,793][13279] Loop rollout_proc4_evt_loop terminating...
+[2025-04-03 13:23:59,793][12851] Component RolloutWorker_w4 stopped!
+[2025-04-03 13:23:59,795][13277] Stopping RolloutWorker_w3...
+[2025-04-03 13:23:59,796][13277] Loop rollout_proc3_evt_loop terminating...
+[2025-04-03 13:23:59,795][12851] Component RolloutWorker_w3 stopped!
+[2025-04-03 13:24:00,143][13260] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2025-04-03 13:24:00,185][13260] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000614_2514944.pth
+[2025-04-03 13:24:00,186][13260] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2025-04-03 13:24:00,239][13260] Stopping LearnerWorker_p0...
+[2025-04-03 13:24:00,239][13260] Loop learner_proc0_evt_loop terminating...
+[2025-04-03 13:24:00,239][12851] Component LearnerWorker_p0 stopped!
+[2025-04-03 13:24:00,241][12851] Waiting for process learner_proc0 to stop...
+[2025-04-03 13:24:00,685][12851] Waiting for process inference_proc0-0 to join...
+[2025-04-03 13:24:00,686][12851] Waiting for process rollout_proc0 to join...
+[2025-04-03 13:24:00,687][12851] Waiting for process rollout_proc1 to join...
+[2025-04-03 13:24:00,688][12851] Waiting for process rollout_proc2 to join...
+[2025-04-03 13:24:00,689][12851] Waiting for process rollout_proc3 to join...
+[2025-04-03 13:24:00,690][12851] Waiting for process rollout_proc4 to join...
+[2025-04-03 13:24:00,691][12851] Waiting for process rollout_proc5 to join...
+[2025-04-03 13:24:00,692][12851] Waiting for process rollout_proc6 to join...
+[2025-04-03 13:24:00,693][12851] Waiting for process rollout_proc7 to join...
+[2025-04-03 13:24:00,694][12851] Batcher 0 profile tree view:
+batching: 0.0147, releasing_batches: 0.0006
+[2025-04-03 13:24:00,694][12851] InferenceWorker_p0-w0 profile tree view:
+update_model: 0.0132
+wait_policy: 0.0000
+  wait_policy_total: 0.8233
+one_step: 0.0019
+  handle_policy_step: 0.9894
+    deserialize: 0.0168, stack: 0.0018, obs_to_device_normalize: 0.1476, forward: 0.7246, send_messages: 0.0278
+    prepare_outputs: 0.0600
+      to_cpu: 0.0475
+[2025-04-03 13:24:00,695][12851] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 0.8629
+train: 0.9255
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0007, kl_divergence: 0.0081, after_optimizer: 0.0339
+  calculate_losses: 0.3417
+    losses_init: 0.0000, forward_head: 0.2302, bptt_initial: 0.0677, tail: 0.0154, advantages_returns: 0.0008, losses: 0.0233
+    bptt: 0.0036
+      bptt_forward_core: 0.0035
+  update: 0.5394
+    clip: 0.0340
+[2025-04-03 13:24:00,696][12851] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0004, enqueue_policy_requests: 0.0178, env_step: 0.1994, overhead: 0.0091, complete_rollouts: 0.0005
+save_policy_outputs: 0.0117
+  split_output_tensors: 0.0042
+[2025-04-03 13:24:00,697][12851] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0003, enqueue_policy_requests: 0.0156, env_step: 0.1938, overhead: 0.0083, complete_rollouts: 0.0003
+save_policy_outputs: 0.0127
+  split_output_tensors: 0.0044
+[2025-04-03 13:24:00,699][12851] Loop Runner_EvtLoop terminating...
+[2025-04-03 13:24:00,699][12851] Runner profile tree view:
+main_loop: 7.7164
+[2025-04-03 13:24:00,700][12851] Collected {0: 4014080}, FPS: 1061.6
+[2025-04-03 13:45:42,593][12851] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 13:45:42,594][12851] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 13:45:42,595][12851] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 13:45:42,595][12851] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 13:45:42,596][12851] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:45:42,596][12851] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 13:45:42,597][12851] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:45:42,597][12851] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 13:45:42,598][12851] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-04-03 13:45:42,598][12851] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-04-03 13:45:42,599][12851] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 13:45:42,600][12851] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 13:45:42,600][12851] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 13:45:42,600][12851] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 13:45:42,601][12851] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 13:45:42,618][12851] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:45:42,621][12851] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:45:42,623][12851] RunningMeanStd input shape: (1,)
+[2025-04-03 13:45:42,632][12851] ConvEncoder: input_channels=3
+[2025-04-03 13:45:42,747][12851] Conv encoder output size: 512
+[2025-04-03 13:45:42,748][12851] Policy head output size: 512
+[2025-04-03 13:45:43,349][12851] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2025-04-03 13:45:44,037][12851] Num frames 100...
+[2025-04-03 13:45:44,124][12851] Num frames 200...
+[2025-04-03 13:45:44,209][12851] Num frames 300...
+[2025-04-03 13:45:44,344][12851] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
+[2025-04-03 13:45:44,345][12851] Avg episode reward: 3.840, avg true_objective: 3.840
+[2025-04-03 13:45:44,365][12851] Num frames 400...
+[2025-04-03 13:45:44,458][12851] Num frames 500...
+[2025-04-03 13:45:44,552][12851] Num frames 600...
+[2025-04-03 13:45:44,645][12851] Num frames 700...
+[2025-04-03 13:45:44,744][12851] Num frames 800...
+[2025-04-03 13:45:44,796][12851] Avg episode rewards: #0: 5.000, true rewards: #0: 4.000
+[2025-04-03 13:45:44,797][12851] Avg episode reward: 5.000, avg true_objective: 4.000
+[2025-04-03 13:45:44,891][12851] Num frames 900...
+[2025-04-03 13:45:44,982][12851] Num frames 1000...
+[2025-04-03 13:45:45,073][12851] Num frames 1100...
+[2025-04-03 13:45:45,166][12851] Num frames 1200...
+[2025-04-03 13:45:45,290][12851] Avg episode rewards: #0: 5.600, true rewards: #0: 4.267
+[2025-04-03 13:45:45,292][12851] Avg episode reward: 5.600, avg true_objective: 4.267
+[2025-04-03 13:45:45,318][12851] Num frames 1300...
+[2025-04-03 13:45:45,408][12851] Num frames 1400...
+[2025-04-03 13:45:45,499][12851] Num frames 1500...
+[2025-04-03 13:45:45,588][12851] Num frames 1600...
+[2025-04-03 13:45:45,696][12851] Avg episode rewards: #0: 5.160, true rewards: #0: 4.160
+[2025-04-03 13:45:45,698][12851] Avg episode reward: 5.160, avg true_objective: 4.160
+[2025-04-03 13:45:45,741][12851] Num frames 1700...
+[2025-04-03 13:45:45,828][12851] Num frames 1800...
+[2025-04-03 13:45:45,917][12851] Num frames 1900...
+[2025-04-03 13:45:46,004][12851] Num frames 2000...
+[2025-04-03 13:45:46,102][12851] Avg episode rewards: #0: 4.896, true rewards: #0: 4.096
+[2025-04-03 13:45:46,104][12851] Avg episode reward: 4.896, avg true_objective: 4.096
+[2025-04-03 13:45:46,158][12851] Num frames 2100...
+[2025-04-03 13:45:46,244][12851] Num frames 2200...
+[2025-04-03 13:45:46,330][12851] Num frames 2300...
+[2025-04-03 13:45:46,415][12851] Num frames 2400...
+[2025-04-03 13:45:46,551][12851] Avg episode rewards: #0: 4.993, true rewards: #0: 4.160
+[2025-04-03 13:45:46,552][12851] Avg episode reward: 4.993, avg true_objective: 4.160
+[2025-04-03 13:45:46,558][12851] Num frames 2500...
+[2025-04-03 13:45:46,646][12851] Num frames 2600...
+[2025-04-03 13:45:46,732][12851] Num frames 2700...
+[2025-04-03 13:45:46,818][12851] Num frames 2800...
+[2025-04-03 13:45:46,904][12851] Num frames 2900...
+[2025-04-03 13:45:46,967][12851] Avg episode rewards: #0: 4.874, true rewards: #0: 4.160
+[2025-04-03 13:45:46,969][12851] Avg episode reward: 4.874, avg true_objective: 4.160
+[2025-04-03 13:45:47,049][12851] Num frames 3000...
+[2025-04-03 13:45:47,134][12851] Num frames 3100...
+[2025-04-03 13:45:47,248][12851] Avg episode rewards: #0: 4.585, true rewards: #0: 3.960
+[2025-04-03 13:45:47,250][12851] Avg episode reward: 4.585, avg true_objective: 3.960
+[2025-04-03 13:45:47,289][12851] Num frames 3200...
+[2025-04-03 13:45:47,374][12851] Num frames 3300...
+[2025-04-03 13:45:47,460][12851] Num frames 3400...
+[2025-04-03 13:45:47,545][12851] Num frames 3500...
+[2025-04-03 13:45:47,634][12851] Num frames 3600...
+[2025-04-03 13:45:47,726][12851] Num frames 3700...
+[2025-04-03 13:45:47,812][12851] Num frames 3800...
+[2025-04-03 13:45:47,900][12851] Avg episode rewards: #0: 5.267, true rewards: #0: 4.267
+[2025-04-03 13:45:47,902][12851] Avg episode reward: 5.267, avg true_objective: 4.267
+[2025-04-03 13:45:47,965][12851] Num frames 3900...
+[2025-04-03 13:45:48,049][12851] Num frames 4000...
+[2025-04-03 13:45:48,136][12851] Num frames 4100...
+[2025-04-03 13:45:48,223][12851] Num frames 4200...
+[2025-04-03 13:45:48,351][12851] Avg episode rewards: #0: 5.288, true rewards: #0: 4.288
+[2025-04-03 13:45:48,353][12851] Avg episode reward: 5.288, avg true_objective: 4.288
+[2025-04-03 13:45:52,594][12851] Replay video saved to /home/haricot/dev/rl-unit8/train_dir/default_experiment/replay.mp4!
+[2025-04-03 13:46:01,664][12851] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 13:46:01,665][12851] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 13:46:01,666][12851] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 13:46:01,666][12851] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 13:46:01,667][12851] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:46:01,667][12851] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 13:46:01,668][12851] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2025-04-03 13:46:01,668][12851] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 13:46:01,669][12851] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2025-04-03 13:46:01,669][12851] Adding new argument 'hf_repository'='Haricot24601/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2025-04-03 13:46:01,670][12851] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 13:46:01,670][12851] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 13:46:01,671][12851] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 13:46:01,672][12851] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 13:46:01,672][12851] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 13:46:01,681][12851] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:46:01,683][12851] RunningMeanStd input shape: (1,)
+[2025-04-03 13:46:01,689][12851] ConvEncoder: input_channels=3
+[2025-04-03 13:46:01,716][12851] Conv encoder output size: 512
+[2025-04-03 13:46:01,718][12851] Policy head output size: 512
+[2025-04-03 13:46:01,747][12851] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2025-04-03 13:46:02,077][12851] Num frames 100...
+[2025-04-03 13:46:02,277][12851] Num frames 200...
+[2025-04-03 13:46:02,432][12851] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
+[2025-04-03 13:46:02,434][12851] Avg episode reward: 2.560, avg true_objective: 2.560
+[2025-04-03 13:46:02,498][12851] Num frames 300...
+[2025-04-03 13:46:02,621][12851] Num frames 400...
+[2025-04-03 13:46:02,742][12851] Num frames 500...
+[2025-04-03 13:46:02,871][12851] Num frames 600...
+[2025-04-03 13:46:02,981][12851] Avg episode rewards: #0: 3.200, true rewards: #0: 3.200
+[2025-04-03 13:46:02,982][12851] Avg episode reward: 3.200, avg true_objective: 3.200
+[2025-04-03 13:46:03,058][12851] Num frames 700...
+[2025-04-03 13:46:03,179][12851] Num frames 800...
+[2025-04-03 13:46:03,310][12851] Num frames 900...
+[2025-04-03 13:46:03,443][12851] Num frames 1000...
+[2025-04-03 13:46:03,606][12851] Avg episode rewards: #0: 3.960, true rewards: #0: 3.627
+[2025-04-03 13:46:03,609][12851] Avg episode reward: 3.960, avg true_objective: 3.627
+[2025-04-03 13:46:03,629][12851] Num frames 1100...
+[2025-04-03 13:46:03,749][12851] Num frames 1200...
+[2025-04-03 13:46:03,880][12851] Num frames 1300...
+[2025-04-03 13:46:04,014][12851] Num frames 1400...
+[2025-04-03 13:46:04,162][12851] Avg episode rewards: #0: 3.930, true rewards: #0: 3.680
+[2025-04-03 13:46:04,164][12851] Avg episode reward: 3.930, avg true_objective: 3.680
+[2025-04-03 13:46:04,209][12851] Num frames 1500...
+[2025-04-03 13:46:04,337][12851] Num frames 1600...
+[2025-04-03 13:46:04,459][12851] Num frames 1700...
+[2025-04-03 13:46:04,599][12851] Num frames 1800...
+[2025-04-03 13:46:04,720][12851] Avg episode rewards: #0: 3.912, true rewards: #0: 3.712
+[2025-04-03 13:46:04,722][12851] Avg episode reward: 3.912, avg true_objective: 3.712
+[2025-04-03 13:46:04,783][12851] Num frames 1900...
+[2025-04-03 13:46:04,909][12851] Num frames 2000...
+[2025-04-03 13:46:05,033][12851] Num frames 2100...
+[2025-04-03 13:46:05,164][12851] Num frames 2200...
+[2025-04-03 13:46:05,267][12851] Avg episode rewards: #0: 3.900, true rewards: #0: 3.733
+[2025-04-03 13:46:05,269][12851] Avg episode reward: 3.900, avg true_objective: 3.733
+[2025-04-03 13:46:05,346][12851] Num frames 2300...
+[2025-04-03 13:46:05,477][12851] Num frames 2400...
+[2025-04-03 13:46:05,605][12851] Num frames 2500...
+[2025-04-03 13:46:05,732][12851] Num frames 2600...
+[2025-04-03 13:46:05,815][12851] Avg episode rewards: #0: 3.891, true rewards: #0: 3.749
+[2025-04-03 13:46:05,817][12851] Avg episode reward: 3.891, avg true_objective: 3.749
+[2025-04-03 13:46:05,921][12851] Num frames 2700...
+[2025-04-03 13:46:06,056][12851] Num frames 2800...
+[2025-04-03 13:46:06,183][12851] Num frames 2900...
+[2025-04-03 13:46:06,310][12851] Num frames 3000...
+[2025-04-03 13:46:06,374][12851] Avg episode rewards: #0: 3.885, true rewards: #0: 3.760
+[2025-04-03 13:46:06,376][12851] Avg episode reward: 3.885, avg true_objective: 3.760
+[2025-04-03 13:46:06,501][12851] Num frames 3100...
+[2025-04-03 13:46:06,635][12851] Num frames 3200...
+[2025-04-03 13:46:06,769][12851] Num frames 3300...
+[2025-04-03 13:46:06,888][12851] Num frames 3400...
+[2025-04-03 13:46:07,043][12851] Avg episode rewards: #0: 4.098, true rewards: #0: 3.876
+[2025-04-03 13:46:07,045][12851] Avg episode reward: 4.098, avg true_objective: 3.876
+[2025-04-03 13:46:07,063][12851] Num frames 3500...
+[2025-04-03 13:46:07,187][12851] Num frames 3600...
+[2025-04-03 13:46:07,309][12851] Num frames 3700...
+[2025-04-03 13:46:07,428][12851] Num frames 3800...
+[2025-04-03 13:46:07,565][12851] Avg episode rewards: #0: 4.072, true rewards: #0: 3.872
+[2025-04-03 13:46:07,567][12851] Avg episode reward: 4.072, avg true_objective: 3.872
+[2025-04-03 13:46:11,212][12851] Replay video saved to /home/haricot/dev/rl-unit8/train_dir/default_experiment/replay.mp4!
+[2025-04-03 13:46:34,233][12851] The model has been pushed to https://huggingface.co/Haricot24601/rl_course_vizdoom_health_gathering_supreme
+[2025-04-03 13:50:34,897][12851] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json
+[2025-04-03 13:50:34,898][12851] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json
+[2025-04-03 13:50:34,898][12851] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line
+[2025-04-03 13:50:34,899][12851] Overriding arg 'train_dir' with value 'train_dir' passed from command line
+[2025-04-03 13:50:34,900][12851] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 13:50:34,900][12851] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file!
+[2025-04-03 13:50:34,901][12851] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file!
+[2025-04-03 13:50:34,901][12851] Adding new argument 'env_gpu_observations'=True that is not in the saved config file!
+[2025-04-03 13:50:34,902][12851] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 13:50:34,902][12851] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 13:50:34,903][12851] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:50:34,903][12851] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 13:50:34,904][12851] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 13:50:34,905][12851] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 13:50:34,905][12851] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-04-03 13:50:34,906][12851] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-04-03 13:50:34,906][12851] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 13:50:34,907][12851] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 13:50:34,908][12851] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 13:50:34,908][12851] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 13:50:34,909][12851] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 13:50:34,919][12851] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:50:34,920][12851] RunningMeanStd input shape: (1,)
+[2025-04-03 13:50:34,927][12851] ConvEncoder: input_channels=3
+[2025-04-03 13:50:34,959][12851] Conv encoder output size: 512
+[2025-04-03 13:50:34,960][12851] Policy head output size: 512
+[2025-04-03 13:50:35,004][12851] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth...
+[2025-04-03 13:50:35,481][12851] Num frames 100...
+[2025-04-03 13:50:35,637][12851] Num frames 200...
+[2025-04-03 13:50:35,761][12851] Num frames 300...
+[2025-04-03 13:50:35,886][12851] Num frames 400...
+[2025-04-03 13:50:36,005][12851] Num frames 500...
+[2025-04-03 13:50:36,127][12851] Num frames 600...
+[2025-04-03 13:50:36,249][12851] Num frames 700...
+[2025-04-03 13:50:36,371][12851] Num frames 800...
+[2025-04-03 13:50:36,483][12851] Num frames 900...
+[2025-04-03 13:50:36,595][12851] Num frames 1000...
+[2025-04-03 13:50:36,719][12851] Num frames 1100...
+[2025-04-03 13:50:36,849][12851] Num frames 1200...
+[2025-04-03 13:50:36,962][12851] Num frames 1300...
+[2025-04-03 13:50:37,091][12851] Num frames 1400...
+[2025-04-03 13:50:37,217][12851] Num frames 1500...
+[2025-04-03 13:50:37,342][12851] Num frames 1600...
+[2025-04-03 13:50:37,462][12851] Num frames 1700...
+[2025-04-03 13:50:37,590][12851] Num frames 1800...
+[2025-04-03 13:50:37,707][12851] Num frames 1900...
+[2025-04-03 13:50:37,841][12851] Num frames 2000...
+[2025-04-03 13:50:37,960][12851] Num frames 2100...
+[2025-04-03 13:50:38,012][12851] Avg episode rewards: #0: 62.999, true rewards: #0: 21.000
+[2025-04-03 13:50:38,013][12851] Avg episode reward: 62.999, avg true_objective: 21.000
+[2025-04-03 13:50:38,130][12851] Num frames 2200...
+[2025-04-03 13:50:38,244][12851] Num frames 2300...
+[2025-04-03 13:50:38,360][12851] Num frames 2400...
+[2025-04-03 13:50:38,475][12851] Num frames 2500...
+[2025-04-03 13:50:38,591][12851] Num frames 2600...
+[2025-04-03 13:50:38,707][12851] Num frames 2700...
+[2025-04-03 13:50:38,837][12851] Num frames 2800...
+[2025-04-03 13:50:38,953][12851] Num frames 2900...
+[2025-04-03 13:50:39,075][12851] Num frames 3000...
+[2025-04-03 13:50:39,200][12851] Num frames 3100...
+[2025-04-03 13:50:39,325][12851] Num frames 3200...
+[2025-04-03 13:50:39,458][12851] Num frames 3300...
+[2025-04-03 13:50:39,578][12851] Num frames 3400...
+[2025-04-03 13:50:39,695][12851] Num frames 3500...
+[2025-04-03 13:50:39,833][12851] Num frames 3600...
+[2025-04-03 13:50:39,971][12851] Num frames 3700...
+[2025-04-03 13:50:40,101][12851] Num frames 3800...
+[2025-04-03 13:50:40,229][12851] Num frames 3900...
+[2025-04-03 13:50:40,347][12851] Num frames 4000...
+[2025-04-03 13:50:40,440][12851] Num frames 4100...
+[2025-04-03 13:50:40,534][12851] Num frames 4200...
+[2025-04-03 13:50:40,586][12851] Avg episode rewards: #0: 64.499, true rewards: #0: 21.000
+[2025-04-03 13:50:40,587][12851] Avg episode reward: 64.499, avg true_objective: 21.000
+[2025-04-03 13:50:40,686][12851] Num frames 4300...
+[2025-04-03 13:50:40,784][12851] Num frames 4400...
+[2025-04-03 13:50:40,881][12851] Num frames 4500...
+[2025-04-03 13:50:40,981][12851] Num frames 4600...
+[2025-04-03 13:50:41,086][12851] Num frames 4700...
+[2025-04-03 13:50:41,179][12851] Num frames 4800...
+[2025-04-03 13:50:41,273][12851] Num frames 4900...
+[2025-04-03 13:50:41,369][12851] Num frames 5000...
+[2025-04-03 13:50:41,463][12851] Num frames 5100...
+[2025-04-03 13:50:41,557][12851] Num frames 5200...
+[2025-04-03 13:50:41,649][12851] Num frames 5300...
+[2025-04-03 13:50:41,744][12851] Num frames 5400...
+[2025-04-03 13:50:41,837][12851] Num frames 5500...
+[2025-04-03 13:50:41,930][12851] Num frames 5600...
+[2025-04-03 13:50:42,028][12851] Num frames 5700...
+[2025-04-03 13:50:42,123][12851] Num frames 5800...
+[2025-04-03 13:50:42,227][12851] Num frames 5900...
+[2025-04-03 13:50:42,331][12851] Num frames 6000...
+[2025-04-03 13:50:42,439][12851] Num frames 6100...
+[2025-04-03 13:50:42,546][12851] Num frames 6200...
+[2025-04-03 13:50:42,655][12851] Num frames 6300...
+[2025-04-03 13:50:42,707][12851] Avg episode rewards: #0: 65.332, true rewards: #0: 21.000
+[2025-04-03 13:50:42,709][12851] Avg episode reward: 65.332, avg true_objective: 21.000
+[2025-04-03 13:50:42,846][12851] Num frames 6400...
+[2025-04-03 13:50:42,983][12851] Num frames 6500...
+[2025-04-03 13:50:43,104][12851] Num frames 6600...
+[2025-04-03 13:50:43,223][12851] Num frames 6700...
+[2025-04-03 13:50:43,346][12851] Num frames 6800...
+[2025-04-03 13:50:43,471][12851] Num frames 6900...
+[2025-04-03 13:50:43,596][12851] Num frames 7000...
+[2025-04-03 13:50:43,717][12851] Num frames 7100...
+[2025-04-03 13:50:43,838][12851] Num frames 7200...
+[2025-04-03 13:50:43,949][12851] Num frames 7300...
+[2025-04-03 13:50:44,061][12851] Num frames 7400...
+[2025-04-03 13:50:44,169][12851] Num frames 7500...
+[2025-04-03 13:50:44,279][12851] Num frames 7600...
+[2025-04-03 13:50:44,395][12851] Num frames 7700...
+[2025-04-03 13:50:44,511][12851] Num frames 7800...
+[2025-04-03 13:50:44,636][12851] Num frames 7900...
+[2025-04-03 13:50:44,779][12851] Num frames 8000...
+[2025-04-03 13:50:44,900][12851] Num frames 8100...
+[2025-04-03 13:50:45,021][12851] Num frames 8200...
+[2025-04-03 13:50:45,145][12851] Num frames 8300...
+[2025-04-03 13:50:45,273][12851] Num frames 8400...
+[2025-04-03 13:50:45,325][12851] Avg episode rewards: #0: 64.999, true rewards: #0: 21.000
+[2025-04-03 13:50:45,327][12851] Avg episode reward: 64.999, avg true_objective: 21.000
+[2025-04-03 13:50:45,461][12851] Num frames 8500...
+[2025-04-03 13:50:45,586][12851] Num frames 8600...
+[2025-04-03 13:50:45,707][12851] Num frames 8700...
+[2025-04-03 13:50:45,828][12851] Num frames 8800...
+[2025-04-03 13:50:45,949][12851] Num frames 8900...
+[2025-04-03 13:50:46,074][12851] Num frames 9000...
+[2025-04-03 13:50:46,192][12851] Num frames 9100...
+[2025-04-03 13:50:46,317][12851] Num frames 9200...
+[2025-04-03 13:50:46,441][12851] Num frames 9300...
+[2025-04-03 13:50:46,567][12851] Num frames 9400...
+[2025-04-03 13:50:46,691][12851] Num frames 9500...
+[2025-04-03 13:50:46,813][12851] Num frames 9600...
+[2025-04-03 13:50:46,932][12851] Num frames 9700...
+[2025-04-03 13:50:47,053][12851] Num frames 9800...
+[2025-04-03 13:50:47,174][12851] Num frames 9900...
+[2025-04-03 13:50:47,299][12851] Num frames 10000...
+[2025-04-03 13:50:47,415][12851] Num frames 10100...
+[2025-04-03 13:50:47,537][12851] Num frames 10200...
+[2025-04-03 13:50:47,655][12851] Num frames 10300...
+[2025-04-03 13:50:47,770][12851] Num frames 10400...
+[2025-04-03 13:50:47,895][12851] Num frames 10500...
+[2025-04-03 13:50:47,946][12851] Avg episode rewards: #0: 64.599, true rewards: #0: 21.000
+[2025-04-03 13:50:47,947][12851] Avg episode reward: 64.599, avg true_objective: 21.000
+[2025-04-03 13:50:48,083][12851] Num frames 10600...
+[2025-04-03 13:50:48,217][12851] Num frames 10700...
+[2025-04-03 13:50:48,330][12851] Num frames 10800...
+[2025-04-03 13:50:48,445][12851] Num frames 10900...
+[2025-04-03 13:50:48,565][12851] Num frames 11000...
+[2025-04-03 13:50:48,689][12851] Num frames 11100...
+[2025-04-03 13:50:48,812][12851] Num frames 11200...
+[2025-04-03 13:50:48,937][12851] Num frames 11300...
+[2025-04-03 13:50:49,074][12851] Avg episode rewards: #0: 58.106, true rewards: #0: 18.940
+[2025-04-03 13:50:49,075][12851] Avg episode reward: 58.106, avg true_objective: 18.940
+[2025-04-03 13:50:49,122][12851] Num frames 11400...
+[2025-04-03 13:50:49,240][12851] Num frames 11500...
+[2025-04-03 13:50:49,363][12851] Num frames 11600...
+[2025-04-03 13:50:49,488][12851] Num frames 11700...
+[2025-04-03 13:50:49,618][12851] Num frames 11800...
+[2025-04-03 13:50:49,742][12851] Num frames 11900...
+[2025-04-03 13:50:49,869][12851] Num frames 12000...
+[2025-04-03 13:50:49,999][12851] Num frames 12100...
+[2025-04-03 13:50:50,129][12851] Num frames 12200...
+[2025-04-03 13:50:50,261][12851] Num frames 12300...
+[2025-04-03 13:50:50,389][12851] Num frames 12400...
+[2025-04-03 13:50:50,512][12851] Num frames 12500...
+[2025-04-03 13:50:50,632][12851] Num frames 12600...
+[2025-04-03 13:50:50,750][12851] Num frames 12700...
+[2025-04-03 13:50:50,879][12851] Num frames 12800...
+[2025-04-03 13:50:50,997][12851] Num frames 12900...
+[2025-04-03 13:50:51,123][12851] Num frames 13000...
+[2025-04-03 13:50:51,259][12851] Num frames 13100...
+[2025-04-03 13:50:51,387][12851] Num frames 13200...
+[2025-04-03 13:50:51,523][12851] Num frames 13300...
+[2025-04-03 13:50:51,649][12851] Num frames 13400...
+[2025-04-03 13:50:51,780][12851] Avg episode rewards: #0: 59.090, true rewards: #0: 19.234
+[2025-04-03 13:50:51,780][12851] Avg episode reward: 59.090, avg true_objective: 19.234
+[2025-04-03 13:50:51,828][12851] Num frames 13500...
+[2025-04-03 13:50:51,936][12851] Num frames 13600...
+[2025-04-03 13:50:52,048][12851] Num frames 13700...
+[2025-04-03 13:50:52,156][12851] Num frames 13800...
+[2025-04-03 13:50:52,271][12851] Num frames 13900...
+[2025-04-03 13:50:52,392][12851] Num frames 14000...
+[2025-04-03 13:50:52,516][12851] Num frames 14100...
+[2025-04-03 13:50:52,628][12851] Num frames 14200...
+[2025-04-03 13:50:52,762][12851] Num frames 14300...
+[2025-04-03 13:50:52,879][12851] Num frames 14400...
+[2025-04-03 13:50:53,004][12851] Num frames 14500...
+[2025-04-03 13:50:53,124][12851] Num frames 14600...
+[2025-04-03 13:50:53,242][12851] Num frames 14700...
+[2025-04-03 13:50:53,366][12851] Num frames 14800...
+[2025-04-03 13:50:53,488][12851] Num frames 14900...
+[2025-04-03 13:50:53,602][12851] Num frames 15000...
+[2025-04-03 13:50:53,711][12851] Num frames 15100...
+[2025-04-03 13:50:53,814][12851] Num frames 15200...
+[2025-04-03 13:50:53,927][12851] Num frames 15300...
+[2025-04-03 13:50:54,043][12851] Num frames 15400...
+[2025-04-03 13:50:54,149][12851] Num frames 15500...
+[2025-04-03 13:50:54,266][12851] Avg episode rewards: #0: 59.579, true rewards: #0: 19.455
+[2025-04-03 13:50:54,268][12851] Avg episode reward: 59.579, avg true_objective: 19.455
+[2025-04-03 13:50:54,315][12851] Num frames 15600...
+[2025-04-03 13:50:54,420][12851] Num frames 15700...
+[2025-04-03 13:50:54,539][12851] Num frames 15800...
+[2025-04-03 13:50:54,652][12851] Num frames 15900...
+[2025-04-03 13:50:54,760][12851] Num frames 16000...
+[2025-04-03 13:50:54,877][12851] Num frames 16100...
+[2025-04-03 13:50:54,986][12851] Num frames 16200...
+[2025-04-03 13:50:55,092][12851] Num frames 16300...
+[2025-04-03 13:50:55,224][12851] Num frames 16400...
+[2025-04-03 13:50:55,359][12851] Num frames 16500...
+[2025-04-03 13:50:55,470][12851] Num frames 16600...
+[2025-04-03 13:50:55,596][12851] Num frames 16700...
+[2025-04-03 13:50:55,721][12851] Num frames 16800...
+[2025-04-03 13:50:55,844][12851] Num frames 16900...
+[2025-04-03 13:50:55,961][12851] Num frames 17000...
+[2025-04-03 13:50:56,087][12851] Num frames 17100...
+[2025-04-03 13:50:56,209][12851] Num frames 17200...
+[2025-04-03 13:50:56,331][12851] Num frames 17300...
+[2025-04-03 13:50:56,449][12851] Num frames 17400...
+[2025-04-03 13:50:56,570][12851] Num frames 17500...
+[2025-04-03 13:50:56,696][12851] Num frames 17600...
+[2025-04-03 13:50:56,832][12851] Avg episode rewards: #0: 59.848, true rewards: #0: 19.627
+[2025-04-03 13:50:56,833][12851] Avg episode reward: 59.848, avg true_objective: 19.627
+[2025-04-03 13:50:56,881][12851] Num frames 17700...
+[2025-04-03 13:50:57,003][12851] Num frames 17800...
+[2025-04-03 13:50:57,125][12851] Num frames 17900...
+[2025-04-03 13:50:57,249][12851] Num frames 18000...
+[2025-04-03 13:50:57,389][12851] Num frames 18100...
+[2025-04-03 13:50:57,543][12851] Num frames 18200...
+[2025-04-03 13:50:57,675][12851] Num frames 18300...
+[2025-04-03 13:50:57,805][12851] Num frames 18400...
+[2025-04-03 13:50:57,915][12851] Num frames 18500...
+[2025-04-03 13:50:58,032][12851] Num frames 18600...
+[2025-04-03 13:50:58,165][12851] Num frames 18700...
+[2025-04-03 13:50:58,301][12851] Num frames 18800...
+[2025-04-03 13:50:58,431][12851] Num frames 18900...
+[2025-04-03 13:50:58,559][12851] Num frames 19000...
+[2025-04-03 13:50:58,674][12851] Num frames 19100...
+[2025-04-03 13:50:58,787][12851] Num frames 19200...
+[2025-04-03 13:50:58,905][12851] Num frames 19300...
+[2025-04-03 13:50:59,017][12851] Num frames 19400...
+[2025-04-03 13:50:59,123][12851] Num frames 19500...
+[2025-04-03 13:50:59,231][12851] Num frames 19600...
+[2025-04-03 13:50:59,339][12851] Num frames 19700...
+[2025-04-03 13:50:59,459][12851] Avg episode rewards: #0: 59.963, true rewards: #0: 19.764
+[2025-04-03 13:50:59,461][12851] Avg episode reward: 59.963, avg true_objective: 19.764
+[2025-04-03 13:51:19,908][12851] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4!
+[2025-04-03 13:57:29,185][12851] Environment doom_basic already registered, overwriting...
+[2025-04-03 13:57:29,186][12851] Environment doom_two_colors_easy already registered, overwriting...
+[2025-04-03 13:57:29,187][12851] Environment doom_two_colors_hard already registered, overwriting...
+[2025-04-03 13:57:29,187][12851] Environment doom_dm already registered, overwriting...
+[2025-04-03 13:57:29,188][12851] Environment doom_dwango5 already registered, overwriting...
+[2025-04-03 13:57:29,189][12851] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2025-04-03 13:57:29,189][12851] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2025-04-03 13:57:29,190][12851] Environment doom_my_way_home already registered, overwriting...
+[2025-04-03 13:57:29,191][12851] Environment doom_deadly_corridor already registered, overwriting...
+[2025-04-03 13:57:29,192][12851] Environment doom_defend_the_center already registered, overwriting...
+[2025-04-03 13:57:29,192][12851] Environment doom_defend_the_line already registered, overwriting...
+[2025-04-03 13:57:29,193][12851] Environment doom_health_gathering already registered, overwriting...
+[2025-04-03 13:57:29,193][12851] Environment doom_health_gathering_supreme already registered, overwriting...
+[2025-04-03 13:57:29,194][12851] Environment doom_battle already registered, overwriting...
+[2025-04-03 13:57:29,195][12851] Environment doom_battle2 already registered, overwriting...
+[2025-04-03 13:57:29,196][12851] Environment doom_duel_bots already registered, overwriting...
+[2025-04-03 13:57:29,196][12851] Environment doom_deathmatch_bots already registered, overwriting...
+[2025-04-03 13:57:29,197][12851] Environment doom_duel already registered, overwriting...
+[2025-04-03 13:57:29,198][12851] Environment doom_deathmatch_full already registered, overwriting...
+[2025-04-03 13:57:29,198][12851] Environment doom_benchmark already registered, overwriting...
+[2025-04-03 13:57:29,199][12851] register_encoder_factory: <function make_vizdoom_encoder at 0x7fd3c472c820>
+[2025-04-03 13:57:29,206][12851] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 13:57:29,206][12851] Overriding arg 'num_workers' with value 13 passed from command line
+[2025-04-03 13:57:29,207][12851] Overriding arg 'train_for_env_steps' with value 40000000 passed from command line
+[2025-04-03 13:57:29,211][12851] Experiment dir /home/haricot/dev/rl-unit8/train_dir/default_experiment already exists!
+[2025-04-03 13:57:29,212][12851] Resuming existing experiment from /home/haricot/dev/rl-unit8/train_dir/default_experiment...
+[2025-04-03 13:57:29,212][12851] Weights and Biases integration disabled
+[2025-04-03 13:57:29,215][12851] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2025-04-03 13:57:30,589][12851] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/home/haricot/dev/rl-unit8/train_dir
+restart_behavior=resume
+device=gpu
+seed=None
+num_policies=1
+async_rl=True
+serial_mode=False
+batched_sampling=False
+num_batches_to_accumulate=2
+worker_num_splits=2
+policy_workers_per_policy=1
+max_policy_lag=1000
+num_workers=13
+num_envs_per_worker=4
+batch_size=1024
+num_batches_per_epoch=1
+num_epochs=1
+rollout=32
+recurrence=32
+shuffle_minibatches=False
+gamma=0.99
+reward_scale=1.0
+reward_clip=1000.0
+value_bootstrap=False
+normalize_returns=True
+exploration_loss_coeff=0.001
+value_loss_coeff=0.5
+kl_loss_coeff=0.0
+exploration_loss=symmetric_kl
+gae_lambda=0.95
+ppo_clip_ratio=0.1
+ppo_clip_value=0.2
+with_vtrace=False
+vtrace_rho=1.0
+vtrace_c=1.0
+optimizer=adam
+adam_eps=1e-06
+adam_beta1=0.9
+adam_beta2=0.999
+max_grad_norm=4.0
+learning_rate=0.0001
+lr_schedule=constant
+lr_schedule_kl_threshold=0.008
+lr_adaptive_min=1e-06
+lr_adaptive_max=0.01
+obs_subtract_mean=0.0
+obs_scale=255.0
+normalize_input=True
+normalize_input_keys=None
+decorrelate_experience_max_seconds=0
+decorrelate_envs_on_one_worker=True
+actor_worker_gpus=[]
+set_workers_cpu_affinity=True
+force_envs_single_thread=False
+default_niceness=0
+log_to_file=True
+experiment_summaries_interval=10
+flush_summaries_interval=30
+stats_avg=100
+summaries_use_frameskip=True
+heartbeat_interval=20
+heartbeat_reporting_interval=600
+train_for_env_steps=40000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2025-04-03 13:57:30,590][12851] Saving configuration to /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json...
+[2025-04-03 13:57:30,591][12851] Rollout worker 0 uses device cpu
+[2025-04-03 13:57:30,592][12851] Rollout worker 1 uses device cpu
+[2025-04-03 13:57:30,593][12851] Rollout worker 2 uses device cpu
+[2025-04-03 13:57:30,593][12851] Rollout worker 3 uses device cpu
+[2025-04-03 13:57:30,594][12851] Rollout worker 4 uses device cpu
+[2025-04-03 13:57:30,594][12851] Rollout worker 5 uses device cpu
+[2025-04-03 13:57:30,595][12851] Rollout worker 6 uses device cpu
+[2025-04-03 13:57:30,596][12851] Rollout worker 7 uses device cpu
+[2025-04-03 13:57:30,596][12851] Rollout worker 8 uses device cpu
+[2025-04-03 13:57:30,597][12851] Rollout worker 9 uses device cpu
+[2025-04-03 13:57:30,598][12851] Rollout worker 10 uses device cpu
+[2025-04-03 13:57:30,598][12851] Rollout worker 11 uses device cpu
+[2025-04-03 13:57:30,599][12851] Rollout worker 12 uses device cpu
+[2025-04-03 13:57:30,639][12851] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:57:30,639][12851] InferenceWorker_p0-w0: min num requests: 4
+[2025-04-03 13:57:30,662][12851] Starting all processes...
+[2025-04-03 13:57:30,663][12851] Starting process learner_proc0
+[2025-04-03 13:57:30,713][12851] Starting all processes...
+[2025-04-03 13:57:30,718][12851] Starting process inference_proc0-0
+[2025-04-03 13:57:30,718][12851] Starting process rollout_proc0
+[2025-04-03 13:57:30,718][12851] Starting process rollout_proc1
+[2025-04-03 13:57:30,719][12851] Starting process rollout_proc2
+[2025-04-03 13:57:30,720][12851] Starting process rollout_proc3
+[2025-04-03 13:57:30,720][12851] Starting process rollout_proc4
+[2025-04-03 13:57:30,720][12851] Starting process rollout_proc5
+[2025-04-03 13:57:30,721][12851] Starting process rollout_proc6
+[2025-04-03 13:57:30,724][12851] Starting process rollout_proc7
+[2025-04-03 13:57:30,725][12851] Starting process rollout_proc8
+[2025-04-03 13:57:30,726][12851] Starting process rollout_proc9
+[2025-04-03 13:57:30,727][12851] Starting process rollout_proc10
+[2025-04-03 13:57:30,733][12851] Starting process rollout_proc11
+[2025-04-03 13:57:30,734][12851] Starting process rollout_proc12
+[2025-04-03 13:57:33,181][20448] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,181][20447] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:57:33,182][20447] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2025-04-03 13:57:33,182][20429] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:57:33,182][20429] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2025-04-03 13:57:33,183][20450] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,190][20449] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,233][20447] Num visible devices: 1
+[2025-04-03 13:57:33,241][20429] Num visible devices: 1
+[2025-04-03 13:57:33,249][20484] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,288][20487] Worker 9 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,317][20482] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,319][20429] Starting seed is not provided
+[2025-04-03 13:57:33,319][20429] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:57:33,319][20429] Initializing actor-critic model on device cuda:0
+[2025-04-03 13:57:33,319][20429] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:57:33,321][20429] RunningMeanStd input shape: (1,)
+[2025-04-03 13:57:33,328][20483] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,334][20429] ConvEncoder: input_channels=3
+[2025-04-03 13:57:33,383][20489] Worker 8 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,383][20491] Worker 12 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,456][20486] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,467][20429] Conv encoder output size: 512
+[2025-04-03 13:57:33,467][20429] Policy head output size: 512
+[2025-04-03 13:57:33,468][20485] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,470][20488] Worker 10 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,491][20490] Worker 11 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
+[2025-04-03 13:57:33,495][20429] Created Actor Critic model with architecture:
+[2025-04-03 13:57:33,495][20429] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2025-04-03 13:57:33,779][20429] Using optimizer <class 'torch.optim.adam.Adam'>
+[2025-04-03 13:57:34,655][20429] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2025-04-03 13:57:34,696][20429] Loading model from checkpoint
+[2025-04-03 13:57:34,697][20429] Loaded experiment state at self.train_step=980, self.env_steps=4014080
+[2025-04-03 13:57:34,697][20429] Initialized policy 0 weights for model version 980
+[2025-04-03 13:57:34,701][20429] LearnerWorker_p0 finished initialization!
+[2025-04-03 13:57:34,701][20429] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2025-04-03 13:57:34,892][20447] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 13:57:34,894][20447] RunningMeanStd input shape: (1,)
+[2025-04-03 13:57:34,901][20447] ConvEncoder: input_channels=3
+[2025-04-03 13:57:34,970][20447] Conv encoder output size: 512
+[2025-04-03 13:57:34,970][20447] Policy head output size: 512
+[2025-04-03 13:57:35,003][12851] Inference worker 0-0 is ready!
+[2025-04-03 13:57:35,004][12851] All inference workers are ready! Signal rollout workers to start!
+[2025-04-03 13:57:35,139][20489] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,140][20488] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,141][20491] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,141][20448] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,142][20449] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,144][20450] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,145][20484] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,145][20482] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,146][20490] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,146][20483] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,149][20486] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,159][20487] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,164][20485] Doom resolution: 160x120, resize resolution: (128, 72)
+[2025-04-03 13:57:35,356][20449] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,356][20484] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,356][20448] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,356][20487] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,360][20489] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,373][20491] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,386][20483] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,400][20450] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,501][20449] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,505][20484] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,513][20491] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,527][20488] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,545][20485] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,546][20482] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,559][20450] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,567][20448] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,653][20487] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,686][20486] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,692][20483] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,702][20449] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:35,724][20491] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:35,729][20488] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,748][20490] Decorrelating experience for 0 frames...
+[2025-04-03 13:57:35,813][20489] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,856][20485] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,868][20484] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:35,889][20486] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:35,905][20483] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:35,914][20487] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:35,917][20449] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:35,928][20448] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,045][20490] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:36,051][20482] Decorrelating experience for 32 frames...
+[2025-04-03 13:57:36,066][20485] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,071][20489] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,105][20488] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,124][20487] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,222][20450] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,234][20484] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,234][20448] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,252][20483] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,268][20485] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,289][20489] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,295][20482] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,312][20488] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,401][20486] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,418][20490] Decorrelating experience for 64 frames...
+[2025-04-03 13:57:36,470][20450] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,576][20491] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,590][20486] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,609][20490] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:36,642][20482] Decorrelating experience for 96 frames...
+[2025-04-03 13:57:37,790][20429] Signal inference workers to stop experience collection...
+[2025-04-03 13:57:37,796][20447] InferenceWorker_p0-w0: stopping experience collection
+[2025-04-03 13:57:39,215][12851] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4014080. Throughput: 0: nan. Samples: 3492. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2025-04-03 13:57:39,217][12851] Avg episode reward: [(0, '1.786')]
+[2025-04-03 13:57:39,772][20429] Signal inference workers to resume experience collection...
+[2025-04-03 13:57:39,772][20447] InferenceWorker_p0-w0: resuming experience collection
+[2025-04-03 13:57:41,326][20447] Updated weights for policy 0, policy_version 990 (0.0147)
+[2025-04-03 13:57:42,619][20447] Updated weights for policy 0, policy_version 1000 (0.0011)
+[2025-04-03 13:57:43,926][20447] Updated weights for policy 0, policy_version 1010 (0.0011)
+[2025-04-03 13:57:44,215][12851] Fps is (10 sec: 26213.9, 60 sec: 26213.9, 300 sec: 26213.9). Total num frames: 4145152. Throughput: 0: 5834.7. Samples: 32666. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2025-04-03 13:57:44,217][12851] Avg episode reward: [(0, '4.283')]
+[2025-04-03 13:57:45,235][20447] Updated weights for policy 0, policy_version 1020 (0.0008)
+[2025-04-03 13:57:46,521][20447] Updated weights for policy 0, policy_version 1030 (0.0012)
+[2025-04-03 13:57:47,810][20447] Updated weights for policy 0, policy_version 1040 (0.0011)
+[2025-04-03 13:57:49,213][20447] Updated weights for policy 0, policy_version 1050 (0.0012)
+[2025-04-03 13:57:49,216][12851] Fps is (10 sec: 28670.9, 60 sec: 28670.9, 300 sec: 28670.9). Total num frames: 4300800. Throughput: 0: 5241.6. Samples: 55910. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2025-04-03 13:57:49,216][12851] Avg episode reward: [(0, '4.232')]
+[2025-04-03 13:57:50,528][20447] Updated weights for policy 0, policy_version 1060 (0.0010)
+[2025-04-03 13:57:50,635][12851] Heartbeat connected on Batcher_0
+[2025-04-03 13:57:50,637][12851] Heartbeat connected on LearnerWorker_p0
+[2025-04-03 13:57:50,643][12851] Heartbeat connected on RolloutWorker_w0
+[2025-04-03 13:57:50,644][12851] Heartbeat connected on InferenceWorker_p0-w0
+[2025-04-03 13:57:50,646][12851] Heartbeat connected on RolloutWorker_w1
+[2025-04-03 13:57:50,647][12851] Heartbeat connected on RolloutWorker_w2
+[2025-04-03 13:57:50,647][12851] Heartbeat connected on RolloutWorker_w3
+[2025-04-03 13:57:50,650][12851] Heartbeat connected on RolloutWorker_w4
+[2025-04-03 13:57:50,651][12851] Heartbeat connected on RolloutWorker_w5
+[2025-04-03 13:57:50,654][12851] Heartbeat connected on RolloutWorker_w7
+[2025-04-03 13:57:50,657][12851] Heartbeat connected on RolloutWorker_w6
+[2025-04-03 13:57:50,658][12851] Heartbeat connected on RolloutWorker_w8
+[2025-04-03 13:57:50,659][12851] Heartbeat connected on RolloutWorker_w9
+[2025-04-03 13:57:50,661][12851] Heartbeat connected on RolloutWorker_w10
+[2025-04-03 13:57:50,662][12851] Heartbeat connected on RolloutWorker_w11
+[2025-04-03 13:57:50,664][12851] Heartbeat connected on RolloutWorker_w12
+[2025-04-03 13:57:51,834][20447] Updated weights for policy 0, policy_version 1070 (0.0011)
+[2025-04-03 13:57:53,208][20447] Updated weights for policy 0, policy_version 1080 (0.0008)
+[2025-04-03 13:57:54,215][12851] Fps is (10 sec: 30720.4, 60 sec: 29218.2, 300 sec: 29218.2). Total num frames: 4452352. Throughput: 0: 6582.0. Samples: 102222. Policy #0 lag: (min: 0.0, avg: 0.8, max: 3.0)
+[2025-04-03 13:57:54,216][12851] Avg episode reward: [(0, '4.515')]
+[2025-04-03 13:57:54,523][20447] Updated weights for policy 0, policy_version 1090 (0.0012)
+[2025-04-03 13:57:55,800][20447] Updated weights for policy 0, policy_version 1100 (0.0010)
+[2025-04-03 13:57:57,081][20447] Updated weights for policy 0, policy_version 1110 (0.0012)
+[2025-04-03 13:57:58,469][20447] Updated weights for policy 0, policy_version 1120 (0.0010)
+[2025-04-03 13:57:59,215][12851] Fps is (10 sec: 31130.7, 60 sec: 29900.7, 300 sec: 29900.7). Total num frames: 4612096. Throughput: 0: 7277.7. Samples: 149046. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:57:59,217][12851] Avg episode reward: [(0, '4.370')]
+[2025-04-03 13:57:59,748][20447] Updated weights for policy 0, policy_version 1130 (0.0010)
+[2025-04-03 13:58:01,086][20447] Updated weights for policy 0, policy_version 1140 (0.0011)
+[2025-04-03 13:58:02,407][20447] Updated weights for policy 0, policy_version 1150 (0.0010)
+[2025-04-03 13:58:03,714][20447] Updated weights for policy 0, policy_version 1160 (0.0011)
+[2025-04-03 13:58:04,215][12851] Fps is (10 sec: 31129.0, 60 sec: 29982.6, 300 sec: 29982.6). Total num frames: 4763648. Throughput: 0: 6746.3. Samples: 172150. Policy #0 lag: (min: 0.0, avg: 1.3, max: 3.0)
+[2025-04-03 13:58:04,216][12851] Avg episode reward: [(0, '4.553')]
+[2025-04-03 13:58:05,025][20447] Updated weights for policy 0, policy_version 1170 (0.0008)
+[2025-04-03 13:58:06,420][20447] Updated weights for policy 0, policy_version 1180 (0.0009)
+[2025-04-03 13:58:07,724][20447] Updated weights for policy 0, policy_version 1190 (0.0010)
+[2025-04-03 13:58:09,026][20447] Updated weights for policy 0, policy_version 1200 (0.0009)
+[2025-04-03 13:58:09,215][12851] Fps is (10 sec: 30720.1, 60 sec: 30173.8, 300 sec: 30173.8). Total num frames: 4919296. Throughput: 0: 7176.4. Samples: 218784. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:58:09,216][12851] Avg episode reward: [(0, '4.572')]
+[2025-04-03 13:58:10,367][20447] Updated weights for policy 0, policy_version 1210 (0.0010)
+[2025-04-03 13:58:11,656][20447] Updated weights for policy 0, policy_version 1220 (0.0010)
+[2025-04-03 13:58:12,941][20447] Updated weights for policy 0, policy_version 1230 (0.0008)
+[2025-04-03 13:58:14,215][12851] Fps is (10 sec: 31130.4, 60 sec: 30310.5, 300 sec: 30310.5). Total num frames: 5074944. Throughput: 0: 7481.6. Samples: 265346. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
+[2025-04-03 13:58:14,216][12851] Avg episode reward: [(0, '4.614')]
+[2025-04-03 13:58:14,243][20447] Updated weights for policy 0, policy_version 1240 (0.0010)
+[2025-04-03 13:58:15,645][20447] Updated weights for policy 0, policy_version 1250 (0.0010)
+[2025-04-03 13:58:16,967][20447] Updated weights for policy 0, policy_version 1260 (0.0009)
+[2025-04-03 13:58:18,277][20447] Updated weights for policy 0, policy_version 1270 (0.0011)
+[2025-04-03 13:58:19,216][12851] Fps is (10 sec: 30719.0, 60 sec: 30310.1, 300 sec: 30310.1). Total num frames: 5226496. Throughput: 0: 7123.4. Samples: 288432. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 13:58:19,217][12851] Avg episode reward: [(0, '4.570')]
+[2025-04-03 13:58:19,657][20447] Updated weights for policy 0, policy_version 1280 (0.0009)
+[2025-04-03 13:58:21,137][20447] Updated weights for policy 0, policy_version 1290 (0.0013)
+[2025-04-03 13:58:22,559][20447] Updated weights for policy 0, policy_version 1300 (0.0011)
+[2025-04-03 13:58:24,030][20447] Updated weights for policy 0, policy_version 1310 (0.0009)
+[2025-04-03 13:58:24,215][12851] Fps is (10 sec: 29491.0, 60 sec: 30128.4, 300 sec: 30128.4). Total num frames: 5369856. Throughput: 0: 7293.6. Samples: 331706. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:58:24,217][12851] Avg episode reward: [(0, '4.302')]
+[2025-04-03 13:58:25,450][20447] Updated weights for policy 0, policy_version 1320 (0.0011)
+[2025-04-03 13:58:26,845][20447] Updated weights for policy 0, policy_version 1330 (0.0010)
+[2025-04-03 13:58:28,237][20447] Updated weights for policy 0, policy_version 1340 (0.0010)
+[2025-04-03 13:58:29,215][12851] Fps is (10 sec: 28673.0, 60 sec: 29982.7, 300 sec: 29982.7). Total num frames: 5513216. Throughput: 0: 7613.8. Samples: 375288. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:58:29,216][12851] Avg episode reward: [(0, '4.261')]
+[2025-04-03 13:58:29,702][20447] Updated weights for policy 0, policy_version 1350 (0.0010)
+[2025-04-03 13:58:31,090][20447] Updated weights for policy 0, policy_version 1360 (0.0010)
+[2025-04-03 13:58:32,509][20447] Updated weights for policy 0, policy_version 1370 (0.0011)
+[2025-04-03 13:58:33,985][20447] Updated weights for policy 0, policy_version 1380 (0.0010)
+[2025-04-03 13:58:34,215][12851] Fps is (10 sec: 28672.0, 60 sec: 29863.6, 300 sec: 29863.6). Total num frames: 5656576. Throughput: 0: 7573.0. Samples: 396694. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 13:58:34,217][12851] Avg episode reward: [(0, '4.471')]
+[2025-04-03 13:58:35,378][20447] Updated weights for policy 0, policy_version 1390 (0.0011)
+[2025-04-03 13:58:36,771][20447] Updated weights for policy 0, policy_version 1400 (0.0011)
+[2025-04-03 13:58:38,167][20447] Updated weights for policy 0, policy_version 1410 (0.0012)
+[2025-04-03 13:58:39,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29832.5, 300 sec: 29832.5). Total num frames: 5804032. Throughput: 0: 7511.4. Samples: 440236. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 13:58:39,216][12851] Avg episode reward: [(0, '4.530')]
+[2025-04-03 13:58:39,610][20447] Updated weights for policy 0, policy_version 1420 (0.0011)
+[2025-04-03 13:58:41,045][20447] Updated weights for policy 0, policy_version 1430 (0.0010)
+[2025-04-03 13:58:42,505][20447] Updated weights for policy 0, policy_version 1440 (0.0010)
+[2025-04-03 13:58:43,936][20447] Updated weights for policy 0, policy_version 1450 (0.0012)
+[2025-04-03 13:58:44,215][12851] Fps is (10 sec: 29081.6, 60 sec: 30037.4, 300 sec: 29743.3). Total num frames: 5947392. Throughput: 0: 7425.7. Samples: 483200. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 13:58:44,217][12851] Avg episode reward: [(0, '4.354')]
+[2025-04-03 13:58:45,339][20447] Updated weights for policy 0, policy_version 1460 (0.0009)
+[2025-04-03 13:58:46,763][20447] Updated weights for policy 0, policy_version 1470 (0.0012)
+[2025-04-03 13:58:48,122][20447] Updated weights for policy 0, policy_version 1480 (0.0009)
+[2025-04-03 13:58:49,215][12851] Fps is (10 sec: 28671.5, 60 sec: 29832.6, 300 sec: 29666.7). Total num frames: 6090752. Throughput: 0: 7389.9. Samples: 504696. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 13:58:49,217][12851] Avg episode reward: [(0, '4.730')]
+[2025-04-03 13:58:49,495][20447] Updated weights for policy 0, policy_version 1490 (0.0011)
+[2025-04-03 13:58:50,913][20447] Updated weights for policy 0, policy_version 1500 (0.0009)
+[2025-04-03 13:58:52,386][20447] Updated weights for policy 0, policy_version 1510 (0.0013)
+[2025-04-03 13:58:53,791][20447] Updated weights for policy 0, policy_version 1520 (0.0012)
+[2025-04-03 13:58:54,215][12851] Fps is (10 sec: 28671.6, 60 sec: 29695.9, 300 sec: 29600.4). Total num frames: 6234112. Throughput: 0: 7330.7. Samples: 548664. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 13:58:54,217][12851] Avg episode reward: [(0, '4.333')]
+[2025-04-03 13:58:55,174][20447] Updated weights for policy 0, policy_version 1530 (0.0010)
+[2025-04-03 13:58:56,607][20447] Updated weights for policy 0, policy_version 1540 (0.0009)
+[2025-04-03 13:58:58,016][20447] Updated weights for policy 0, policy_version 1550 (0.0011)
+[2025-04-03 13:58:59,215][12851] Fps is (10 sec: 29082.3, 60 sec: 29491.2, 300 sec: 29593.6). Total num frames: 6381568. Throughput: 0: 7253.5. Samples: 591756. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:58:59,216][12851] Avg episode reward: [(0, '4.389')]
+[2025-04-03 13:58:59,459][20447] Updated weights for policy 0, policy_version 1560 (0.0012)
+[2025-04-03 13:59:00,955][20447] Updated weights for policy 0, policy_version 1570 (0.0010)
+[2025-04-03 13:59:02,416][20447] Updated weights for policy 0, policy_version 1580 (0.0012)
+[2025-04-03 13:59:03,848][20447] Updated weights for policy 0, policy_version 1590 (0.0011)
+[2025-04-03 13:59:04,215][12851] Fps is (10 sec: 28672.0, 60 sec: 29286.4, 300 sec: 29491.2). Total num frames: 6520832. Throughput: 0: 7209.5. Samples: 612856. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 13:59:04,217][12851] Avg episode reward: [(0, '4.502')]
+[2025-04-03 13:59:05,405][20447] Updated weights for policy 0, policy_version 1600 (0.0011)
+[2025-04-03 13:59:06,862][20447] Updated weights for policy 0, policy_version 1610 (0.0011)
+[2025-04-03 13:59:08,276][20447] Updated weights for policy 0, policy_version 1620 (0.0010)
+[2025-04-03 13:59:09,215][12851] Fps is (10 sec: 27852.6, 60 sec: 29013.3, 300 sec: 29400.2). Total num frames: 6660096. Throughput: 0: 7169.8. Samples: 654348. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 13:59:09,216][12851] Avg episode reward: [(0, '4.450')]
+[2025-04-03 13:59:09,737][20447] Updated weights for policy 0, policy_version 1630 (0.0012)
+[2025-04-03 13:59:11,190][20447] Updated weights for policy 0, policy_version 1640 (0.0009)
+[2025-04-03 13:59:12,615][20447] Updated weights for policy 0, policy_version 1650 (0.0010)
+[2025-04-03 13:59:14,056][20447] Updated weights for policy 0, policy_version 1660 (0.0012)
+[2025-04-03 13:59:14,215][12851] Fps is (10 sec: 28262.7, 60 sec: 28808.5, 300 sec: 29361.8). Total num frames: 6803456. Throughput: 0: 7155.2. Samples: 697274. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 13:59:14,217][12851] Avg episode reward: [(0, '4.391')]
+[2025-04-03 13:59:15,493][20447] Updated weights for policy 0, policy_version 1670 (0.0009)
+[2025-04-03 13:59:16,907][20447] Updated weights for policy 0, policy_version 1680 (0.0011)
+[2025-04-03 13:59:18,352][20447] Updated weights for policy 0, policy_version 1690 (0.0011)
+[2025-04-03 13:59:19,215][12851] Fps is (10 sec: 28262.1, 60 sec: 28603.8, 300 sec: 29286.4). Total num frames: 6942720. Throughput: 0: 7153.4. Samples: 718596. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 13:59:19,217][12851] Avg episode reward: [(0, '4.369')]
+[2025-04-03 13:59:19,833][20447] Updated weights for policy 0, policy_version 1700 (0.0010)
+[2025-04-03 13:59:21,306][20447] Updated weights for policy 0, policy_version 1710 (0.0011)
+[2025-04-03 13:59:22,717][20447] Updated weights for policy 0, policy_version 1720 (0.0010)
+[2025-04-03 13:59:24,123][20447] Updated weights for policy 0, policy_version 1730 (0.0012)
+[2025-04-03 13:59:24,215][12851] Fps is (10 sec: 28261.9, 60 sec: 28603.6, 300 sec: 29257.1). Total num frames: 7086080. Throughput: 0: 7131.9. Samples: 761174. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:59:24,217][12851] Avg episode reward: [(0, '4.541')]
+[2025-04-03 13:59:25,579][20447] Updated weights for policy 0, policy_version 1740 (0.0011)
+[2025-04-03 13:59:26,983][20447] Updated weights for policy 0, policy_version 1750 (0.0010)
+[2025-04-03 13:59:28,385][20447] Updated weights for policy 0, policy_version 1760 (0.0010)
+[2025-04-03 13:59:29,215][12851] Fps is (10 sec: 28672.1, 60 sec: 28603.7, 300 sec: 29230.5). Total num frames: 7229440. Throughput: 0: 7130.6. Samples: 804078. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 13:59:29,217][12851] Avg episode reward: [(0, '4.464')]
+[2025-04-03 13:59:29,222][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001765_7229440.pth...
+[2025-04-03 13:59:29,276][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2025-04-03 13:59:29,892][20447] Updated weights for policy 0, policy_version 1770 (0.0010)
+[2025-04-03 13:59:31,327][20447] Updated weights for policy 0, policy_version 1780 (0.0011)
+[2025-04-03 13:59:32,745][20447] Updated weights for policy 0, policy_version 1790 (0.0009)
+[2025-04-03 13:59:34,215][12851] Fps is (10 sec: 28263.0, 60 sec: 28535.5, 300 sec: 29170.6). Total num frames: 7368704. Throughput: 0: 7127.9. Samples: 825452. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 13:59:34,216][12851] Avg episode reward: [(0, '4.425')]
+[2025-04-03 13:59:34,248][20447] Updated weights for policy 0, policy_version 1800 (0.0011)
+[2025-04-03 13:59:35,672][20447] Updated weights for policy 0, policy_version 1810 (0.0009)
+[2025-04-03 13:59:37,071][20447] Updated weights for policy 0, policy_version 1820 (0.0010)
+[2025-04-03 13:59:38,516][20447] Updated weights for policy 0, policy_version 1830 (0.0010)
+[2025-04-03 13:59:39,216][12851] Fps is (10 sec: 28262.0, 60 sec: 28467.1, 300 sec: 29149.8). Total num frames: 7512064. Throughput: 0: 7090.9. Samples: 867754. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 13:59:39,217][12851] Avg episode reward: [(0, '4.433')]
+[2025-04-03 13:59:39,960][20447] Updated weights for policy 0, policy_version 1840 (0.0009)
+[2025-04-03 13:59:41,479][20447] Updated weights for policy 0, policy_version 1850 (0.0011)
+[2025-04-03 13:59:42,898][20447] Updated weights for policy 0, policy_version 1860 (0.0011)
+[2025-04-03 13:59:44,215][12851] Fps is (10 sec: 28672.0, 60 sec: 28467.2, 300 sec: 29130.8). Total num frames: 7655424. Throughput: 0: 7079.1. Samples: 910316. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:59:44,216][12851] Avg episode reward: [(0, '4.294')]
+[2025-04-03 13:59:44,324][20447] Updated weights for policy 0, policy_version 1870 (0.0009)
+[2025-04-03 13:59:45,769][20447] Updated weights for policy 0, policy_version 1880 (0.0012)
+[2025-04-03 13:59:47,191][20447] Updated weights for policy 0, policy_version 1890 (0.0010)
+[2025-04-03 13:59:48,673][20447] Updated weights for policy 0, policy_version 1900 (0.0011)
+[2025-04-03 13:59:49,215][12851] Fps is (10 sec: 28262.6, 60 sec: 28399.0, 300 sec: 29081.6). Total num frames: 7794688. Throughput: 0: 7080.3. Samples: 931470. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:59:49,217][12851] Avg episode reward: [(0, '4.470')]
+[2025-04-03 13:59:50,123][20447] Updated weights for policy 0, policy_version 1910 (0.0011)
+[2025-04-03 13:59:51,532][20447] Updated weights for policy 0, policy_version 1920 (0.0010)
+[2025-04-03 13:59:53,006][20447] Updated weights for policy 0, policy_version 1930 (0.0010)
+[2025-04-03 13:59:54,215][12851] Fps is (10 sec: 28262.3, 60 sec: 28399.0, 300 sec: 29066.4). Total num frames: 7938048. Throughput: 0: 7103.3. Samples: 973996. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 13:59:54,216][12851] Avg episode reward: [(0, '4.331')]
+[2025-04-03 13:59:54,439][20447] Updated weights for policy 0, policy_version 1940 (0.0009)
+[2025-04-03 13:59:55,823][20447] Updated weights for policy 0, policy_version 1950 (0.0010)
+[2025-04-03 13:59:57,274][20447] Updated weights for policy 0, policy_version 1960 (0.0010)
+[2025-04-03 13:59:58,722][20447] Updated weights for policy 0, policy_version 1970 (0.0010)
+[2025-04-03 13:59:59,215][12851] Fps is (10 sec: 28672.3, 60 sec: 28330.6, 300 sec: 29052.3). Total num frames: 8081408. Throughput: 0: 7109.4. Samples: 1017196. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 13:59:59,216][12851] Avg episode reward: [(0, '4.542')]
+[2025-04-03 14:00:00,107][20447] Updated weights for policy 0, policy_version 1980 (0.0011)
+[2025-04-03 14:00:01,586][20447] Updated weights for policy 0, policy_version 1990 (0.0011)
+[2025-04-03 14:00:02,980][20447] Updated weights for policy 0, policy_version 2000 (0.0011)
+[2025-04-03 14:00:04,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28399.0, 300 sec: 29039.2). Total num frames: 8224768. Throughput: 0: 7108.3. Samples: 1038468. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:00:04,216][12851] Avg episode reward: [(0, '4.455')]
+[2025-04-03 14:00:04,376][20447] Updated weights for policy 0, policy_version 2010 (0.0010)
+[2025-04-03 14:00:05,762][20447] Updated weights for policy 0, policy_version 2020 (0.0010)
+[2025-04-03 14:00:07,206][20447] Updated weights for policy 0, policy_version 2030 (0.0009)
+[2025-04-03 14:00:08,621][20447] Updated weights for policy 0, policy_version 2040 (0.0010)
+[2025-04-03 14:00:09,215][12851] Fps is (10 sec: 29081.7, 60 sec: 28535.5, 300 sec: 29054.3). Total num frames: 8372224. Throughput: 0: 7136.8. Samples: 1082328. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:00:09,216][12851] Avg episode reward: [(0, '4.517')]
+[2025-04-03 14:00:10,002][20447] Updated weights for policy 0, policy_version 2050 (0.0011)
+[2025-04-03 14:00:11,397][20447] Updated weights for policy 0, policy_version 2060 (0.0011)
+[2025-04-03 14:00:12,826][20447] Updated weights for policy 0, policy_version 2070 (0.0013)
+[2025-04-03 14:00:14,215][12851] Fps is (10 sec: 29081.3, 60 sec: 28535.4, 300 sec: 29041.9). Total num frames: 8515584. Throughput: 0: 7143.4. Samples: 1125532. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:00:14,217][12851] Avg episode reward: [(0, '4.355')]
+[2025-04-03 14:00:14,265][20447] Updated weights for policy 0, policy_version 2080 (0.0011)
+[2025-04-03 14:00:15,732][20447] Updated weights for policy 0, policy_version 2090 (0.0012)
+[2025-04-03 14:00:17,164][20447] Updated weights for policy 0, policy_version 2100 (0.0012)
+[2025-04-03 14:00:18,594][20447] Updated weights for policy 0, policy_version 2110 (0.0011)
+[2025-04-03 14:00:19,215][12851] Fps is (10 sec: 28671.6, 60 sec: 28603.7, 300 sec: 29030.4). Total num frames: 8658944. Throughput: 0: 7145.7. Samples: 1147008. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:00:19,217][12851] Avg episode reward: [(0, '4.435')]
+[2025-04-03 14:00:19,984][20447] Updated weights for policy 0, policy_version 2120 (0.0009)
+[2025-04-03 14:00:21,382][20447] Updated weights for policy 0, policy_version 2130 (0.0010)
+[2025-04-03 14:00:22,776][20447] Updated weights for policy 0, policy_version 2140 (0.0012)
+[2025-04-03 14:00:24,216][12851] Fps is (10 sec: 28671.8, 60 sec: 28603.7, 300 sec: 29019.5). Total num frames: 8802304. Throughput: 0: 7173.6. Samples: 1190568. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:00:24,218][12851] Avg episode reward: [(0, '4.481')]
+[2025-04-03 14:00:24,267][20447] Updated weights for policy 0, policy_version 2150 (0.0012)
+[2025-04-03 14:00:25,716][20447] Updated weights for policy 0, policy_version 2160 (0.0010)
+[2025-04-03 14:00:27,130][20447] Updated weights for policy 0, policy_version 2170 (0.0011)
+[2025-04-03 14:00:28,540][20447] Updated weights for policy 0, policy_version 2180 (0.0010)
+[2025-04-03 14:00:29,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28603.7, 300 sec: 29009.3). Total num frames: 8945664. Throughput: 0: 7179.6. Samples: 1233400. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:00:29,216][12851] Avg episode reward: [(0, '4.517')]
+[2025-04-03 14:00:29,968][20447] Updated weights for policy 0, policy_version 2190 (0.0010)
+[2025-04-03 14:00:31,357][20447] Updated weights for policy 0, policy_version 2200 (0.0008)
+[2025-04-03 14:00:32,797][20447] Updated weights for policy 0, policy_version 2210 (0.0013)
+[2025-04-03 14:00:34,215][12851] Fps is (10 sec: 28672.5, 60 sec: 28672.0, 300 sec: 28999.7). Total num frames: 9089024. Throughput: 0: 7187.3. Samples: 1254896. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:00:34,216][12851] Avg episode reward: [(0, '4.328')]
+[2025-04-03 14:00:34,253][20447] Updated weights for policy 0, policy_version 2220 (0.0010)
+[2025-04-03 14:00:35,698][20447] Updated weights for policy 0, policy_version 2230 (0.0011)
+[2025-04-03 14:00:37,133][20447] Updated weights for policy 0, policy_version 2240 (0.0011)
+[2025-04-03 14:00:38,596][20447] Updated weights for policy 0, policy_version 2250 (0.0012)
+[2025-04-03 14:00:39,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28672.1, 300 sec: 28990.6). Total num frames: 9232384. Throughput: 0: 7194.1. Samples: 1297728. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:00:39,217][12851] Avg episode reward: [(0, '4.607')]
+[2025-04-03 14:00:40,025][20447] Updated weights for policy 0, policy_version 2260 (0.0012)
+[2025-04-03 14:00:41,432][20447] Updated weights for policy 0, policy_version 2270 (0.0010)
+[2025-04-03 14:00:42,859][20447] Updated weights for policy 0, policy_version 2280 (0.0009)
+[2025-04-03 14:00:44,215][12851] Fps is (10 sec: 28671.9, 60 sec: 28672.0, 300 sec: 28982.0). Total num frames: 9375744. Throughput: 0: 7183.5. Samples: 1340454. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:00:44,217][12851] Avg episode reward: [(0, '4.229')]
+[2025-04-03 14:00:44,317][20447] Updated weights for policy 0, policy_version 2290 (0.0009)
+[2025-04-03 14:00:45,765][20447] Updated weights for policy 0, policy_version 2300 (0.0013)
+[2025-04-03 14:00:47,233][20447] Updated weights for policy 0, policy_version 2310 (0.0009)
+[2025-04-03 14:00:48,661][20447] Updated weights for policy 0, policy_version 2320 (0.0009)
+[2025-04-03 14:00:49,215][12851] Fps is (10 sec: 28262.3, 60 sec: 28672.0, 300 sec: 28952.2). Total num frames: 9515008. Throughput: 0: 7184.9. Samples: 1361790. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:00:49,216][12851] Avg episode reward: [(0, '4.552')]
+[2025-04-03 14:00:50,108][20447] Updated weights for policy 0, policy_version 2330 (0.0011)
+[2025-04-03 14:00:51,580][20447] Updated weights for policy 0, policy_version 2340 (0.0009)
+[2025-04-03 14:00:53,143][20447] Updated weights for policy 0, policy_version 2350 (0.0013)
+[2025-04-03 14:00:54,215][12851] Fps is (10 sec: 27442.9, 60 sec: 28535.4, 300 sec: 28903.0). Total num frames: 9650176. Throughput: 0: 7128.6. Samples: 1403114. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:00:54,218][12851] Avg episode reward: [(0, '4.333')]
+[2025-04-03 14:00:54,720][20447] Updated weights for policy 0, policy_version 2360 (0.0015)
+[2025-04-03 14:00:56,158][20447] Updated weights for policy 0, policy_version 2370 (0.0010)
+[2025-04-03 14:00:57,588][20447] Updated weights for policy 0, policy_version 2380 (0.0009)
+[2025-04-03 14:00:58,961][20447] Updated weights for policy 0, policy_version 2390 (0.0011)
+[2025-04-03 14:00:59,215][12851] Fps is (10 sec: 27852.8, 60 sec: 28535.5, 300 sec: 28897.3). Total num frames: 9793536. Throughput: 0: 7106.3. Samples: 1445316. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:00:59,217][12851] Avg episode reward: [(0, '4.357')]
+[2025-04-03 14:01:00,370][20447] Updated weights for policy 0, policy_version 2400 (0.0012)
+[2025-04-03 14:01:01,817][20447] Updated weights for policy 0, policy_version 2410 (0.0010)
+[2025-04-03 14:01:03,241][20447] Updated weights for policy 0, policy_version 2420 (0.0011)
+[2025-04-03 14:01:04,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28535.4, 300 sec: 28891.8). Total num frames: 9936896. Throughput: 0: 7104.4. Samples: 1466704. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:01:04,216][12851] Avg episode reward: [(0, '4.293')]
+[2025-04-03 14:01:04,700][20447] Updated weights for policy 0, policy_version 2430 (0.0009)
+[2025-04-03 14:01:06,133][20447] Updated weights for policy 0, policy_version 2440 (0.0009)
+[2025-04-03 14:01:07,545][20447] Updated weights for policy 0, policy_version 2450 (0.0008)
+[2025-04-03 14:01:08,977][20447] Updated weights for policy 0, policy_version 2460 (0.0009)
+[2025-04-03 14:01:09,215][12851] Fps is (10 sec: 28672.0, 60 sec: 28467.2, 300 sec: 28886.6). Total num frames: 10080256. Throughput: 0: 7091.9. Samples: 1509702. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:01:09,216][12851] Avg episode reward: [(0, '4.663')]
+[2025-04-03 14:01:10,383][20447] Updated weights for policy 0, policy_version 2470 (0.0012)
+[2025-04-03 14:01:11,806][20447] Updated weights for policy 0, policy_version 2480 (0.0009)
+[2025-04-03 14:01:13,222][20447] Updated weights for policy 0, policy_version 2490 (0.0010)
+[2025-04-03 14:01:14,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28467.2, 300 sec: 28881.6). Total num frames: 10223616. Throughput: 0: 7098.5. Samples: 1552832. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:01:14,216][12851] Avg episode reward: [(0, '4.483')]
+[2025-04-03 14:01:14,654][20447] Updated weights for policy 0, policy_version 2500 (0.0011)
+[2025-04-03 14:01:16,131][20447] Updated weights for policy 0, policy_version 2510 (0.0010)
+[2025-04-03 14:01:17,532][20447] Updated weights for policy 0, policy_version 2520 (0.0008)
+[2025-04-03 14:01:18,934][20447] Updated weights for policy 0, policy_version 2530 (0.0010)
+[2025-04-03 14:01:19,215][12851] Fps is (10 sec: 29081.7, 60 sec: 28535.5, 300 sec: 28895.4). Total num frames: 10371072. Throughput: 0: 7098.8. Samples: 1574340. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:01:19,216][12851] Avg episode reward: [(0, '4.339')]
+[2025-04-03 14:01:20,356][20447] Updated weights for policy 0, policy_version 2540 (0.0010)
+[2025-04-03 14:01:21,775][20447] Updated weights for policy 0, policy_version 2550 (0.0010)
+[2025-04-03 14:01:23,186][20447] Updated weights for policy 0, policy_version 2560 (0.0012)
+[2025-04-03 14:01:24,215][12851] Fps is (10 sec: 29081.5, 60 sec: 28535.5, 300 sec: 28890.4). Total num frames: 10514432. Throughput: 0: 7114.7. Samples: 1617892. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:01:24,217][12851] Avg episode reward: [(0, '4.419')]
+[2025-04-03 14:01:24,660][20447] Updated weights for policy 0, policy_version 2570 (0.0009)
+[2025-04-03 14:01:26,086][20447] Updated weights for policy 0, policy_version 2580 (0.0011)
+[2025-04-03 14:01:27,489][20447] Updated weights for policy 0, policy_version 2590 (0.0010)
+[2025-04-03 14:01:28,889][20447] Updated weights for policy 0, policy_version 2600 (0.0010)
+[2025-04-03 14:01:29,215][12851] Fps is (10 sec: 28671.9, 60 sec: 28535.5, 300 sec: 28885.7). Total num frames: 10657792. Throughput: 0: 7120.9. Samples: 1660894. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:01:29,216][12851] Avg episode reward: [(0, '4.551')]
+[2025-04-03 14:01:29,223][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002602_10657792.pth...
+[2025-04-03 14:01:29,374][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth
+[2025-04-03 14:01:30,308][20447] Updated weights for policy 0, policy_version 2610 (0.0010)
+[2025-04-03 14:01:31,709][20447] Updated weights for policy 0, policy_version 2620 (0.0010)
+[2025-04-03 14:01:33,164][20447] Updated weights for policy 0, policy_version 2630 (0.0011)
+[2025-04-03 14:01:34,215][12851] Fps is (10 sec: 28672.0, 60 sec: 28535.5, 300 sec: 28881.2). Total num frames: 10801152. Throughput: 0: 7128.8. Samples: 1682588. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:01:34,216][12851] Avg episode reward: [(0, '4.688')]
+[2025-04-03 14:01:34,620][20447] Updated weights for policy 0, policy_version 2640 (0.0009)
+[2025-04-03 14:01:36,020][20447] Updated weights for policy 0, policy_version 2650 (0.0010)
+[2025-04-03 14:01:37,420][20447] Updated weights for policy 0, policy_version 2660 (0.0011)
+[2025-04-03 14:01:38,808][20447] Updated weights for policy 0, policy_version 2670 (0.0009)
+[2025-04-03 14:01:39,215][12851] Fps is (10 sec: 28672.0, 60 sec: 28535.5, 300 sec: 28876.8). Total num frames: 10944512. Throughput: 0: 7171.4. Samples: 1725828. Policy #0 lag: (min: 0.0, avg: 0.9, max: 3.0)
+[2025-04-03 14:01:39,217][12851] Avg episode reward: [(0, '4.395')]
+[2025-04-03 14:01:40,184][20447] Updated weights for policy 0, policy_version 2680 (0.0011)
+[2025-04-03 14:01:41,586][20447] Updated weights for policy 0, policy_version 2690 (0.0012)
+[2025-04-03 14:01:43,033][20447] Updated weights for policy 0, policy_version 2700 (0.0010)
+[2025-04-03 14:01:44,215][12851] Fps is (10 sec: 29081.5, 60 sec: 28603.7, 300 sec: 28889.3). Total num frames: 11091968. Throughput: 0: 7207.4. Samples: 1769648. Policy #0 lag: (min: 0.0, avg: 0.9, max: 3.0)
+[2025-04-03 14:01:44,217][12851] Avg episode reward: [(0, '4.103')]
+[2025-04-03 14:01:44,439][20447] Updated weights for policy 0, policy_version 2710 (0.0011)
+[2025-04-03 14:01:45,831][20447] Updated weights for policy 0, policy_version 2720 (0.0011)
+[2025-04-03 14:01:47,224][20447] Updated weights for policy 0, policy_version 2730 (0.0010)
+[2025-04-03 14:01:48,594][20447] Updated weights for policy 0, policy_version 2740 (0.0011)
+[2025-04-03 14:01:49,215][12851] Fps is (10 sec: 29491.2, 60 sec: 28740.3, 300 sec: 28901.4). Total num frames: 11239424. Throughput: 0: 7220.7. Samples: 1791636. Policy #0 lag: (min: 0.0, avg: 0.9, max: 3.0)
+[2025-04-03 14:01:49,216][12851] Avg episode reward: [(0, '4.206')]
+[2025-04-03 14:01:49,992][20447] Updated weights for policy 0, policy_version 2750 (0.0011)
+[2025-04-03 14:01:51,453][20447] Updated weights for policy 0, policy_version 2760 (0.0010)
+[2025-04-03 14:01:52,852][20447] Updated weights for policy 0, policy_version 2770 (0.0011)
+[2025-04-03 14:01:54,215][12851] Fps is (10 sec: 29081.2, 60 sec: 28876.8, 300 sec: 28896.9). Total num frames: 11382784. Throughput: 0: 7238.8. Samples: 1835450. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:01:54,217][12851] Avg episode reward: [(0, '4.545')]
+[2025-04-03 14:01:54,232][20447] Updated weights for policy 0, policy_version 2780 (0.0012)
+[2025-04-03 14:01:55,648][20447] Updated weights for policy 0, policy_version 2790 (0.0009)
+[2025-04-03 14:01:57,032][20447] Updated weights for policy 0, policy_version 2800 (0.0011)
+[2025-04-03 14:01:58,409][20447] Updated weights for policy 0, policy_version 2810 (0.0011)
+[2025-04-03 14:01:59,215][12851] Fps is (10 sec: 29081.6, 60 sec: 28945.1, 300 sec: 28908.3). Total num frames: 11530240. Throughput: 0: 7254.3. Samples: 1879276. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:01:59,217][12851] Avg episode reward: [(0, '4.552')]
+[2025-04-03 14:01:59,795][20447] Updated weights for policy 0, policy_version 2820 (0.0010)
+[2025-04-03 14:02:01,233][20447] Updated weights for policy 0, policy_version 2830 (0.0010)
+[2025-04-03 14:02:02,621][20447] Updated weights for policy 0, policy_version 2840 (0.0012)
+[2025-04-03 14:02:04,014][20447] Updated weights for policy 0, policy_version 2850 (0.0009)
+[2025-04-03 14:02:04,215][12851] Fps is (10 sec: 29491.6, 60 sec: 29013.4, 300 sec: 28919.3). Total num frames: 11677696. Throughput: 0: 7267.3. Samples: 1901370. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:02:04,216][12851] Avg episode reward: [(0, '4.410')]
+[2025-04-03 14:02:05,406][20447] Updated weights for policy 0, policy_version 2860 (0.0008)
+[2025-04-03 14:02:06,785][20447] Updated weights for policy 0, policy_version 2870 (0.0010)
+[2025-04-03 14:02:08,205][20447] Updated weights for policy 0, policy_version 2880 (0.0009)
+[2025-04-03 14:02:09,215][12851] Fps is (10 sec: 29081.4, 60 sec: 29013.3, 300 sec: 28914.7). Total num frames: 11821056. Throughput: 0: 7274.3. Samples: 1945234. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:02:09,216][12851] Avg episode reward: [(0, '4.364')]
+[2025-04-03 14:02:09,662][20447] Updated weights for policy 0, policy_version 2890 (0.0010)
+[2025-04-03 14:02:11,050][20447] Updated weights for policy 0, policy_version 2900 (0.0010)
+[2025-04-03 14:02:12,432][20447] Updated weights for policy 0, policy_version 2910 (0.0010)
+[2025-04-03 14:02:13,825][20447] Updated weights for policy 0, policy_version 2920 (0.0010)
+[2025-04-03 14:02:14,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29081.5, 300 sec: 28925.2). Total num frames: 11968512. Throughput: 0: 7293.6. Samples: 1989108. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:02:14,216][12851] Avg episode reward: [(0, '4.239')]
+[2025-04-03 14:02:15,225][20447] Updated weights for policy 0, policy_version 2930 (0.0012)
+[2025-04-03 14:02:16,617][20447] Updated weights for policy 0, policy_version 2940 (0.0009)
+[2025-04-03 14:02:17,991][20447] Updated weights for policy 0, policy_version 2950 (0.0011)
+[2025-04-03 14:02:19,215][12851] Fps is (10 sec: 29491.3, 60 sec: 29081.6, 300 sec: 28935.3). Total num frames: 12115968. Throughput: 0: 7299.2. Samples: 2011054. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:19,216][12851] Avg episode reward: [(0, '4.261')]
+[2025-04-03 14:02:19,443][20447] Updated weights for policy 0, policy_version 2960 (0.0011)
+[2025-04-03 14:02:20,865][20447] Updated weights for policy 0, policy_version 2970 (0.0009)
+[2025-04-03 14:02:22,227][20447] Updated weights for policy 0, policy_version 2980 (0.0010)
+[2025-04-03 14:02:23,599][20447] Updated weights for policy 0, policy_version 2990 (0.0009)
+[2025-04-03 14:02:24,215][12851] Fps is (10 sec: 29491.6, 60 sec: 29149.9, 300 sec: 28945.1). Total num frames: 12263424. Throughput: 0: 7317.7. Samples: 2055124. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:02:24,216][12851] Avg episode reward: [(0, '4.483')]
+[2025-04-03 14:02:24,982][20447] Updated weights for policy 0, policy_version 3000 (0.0011)
+[2025-04-03 14:02:26,357][20447] Updated weights for policy 0, policy_version 3010 (0.0010)
+[2025-04-03 14:02:27,798][20447] Updated weights for policy 0, policy_version 3020 (0.0009)
+[2025-04-03 14:02:29,179][20447] Updated weights for policy 0, policy_version 3030 (0.0010)
+[2025-04-03 14:02:29,215][12851] Fps is (10 sec: 29491.0, 60 sec: 29218.1, 300 sec: 28954.5). Total num frames: 12410880. Throughput: 0: 7324.6. Samples: 2099256. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:02:29,217][12851] Avg episode reward: [(0, '4.495')]
+[2025-04-03 14:02:30,610][20447] Updated weights for policy 0, policy_version 3040 (0.0009)
+[2025-04-03 14:02:31,990][20447] Updated weights for policy 0, policy_version 3050 (0.0010)
+[2025-04-03 14:02:33,352][20447] Updated weights for policy 0, policy_version 3060 (0.0009)
+[2025-04-03 14:02:34,215][12851] Fps is (10 sec: 29491.3, 60 sec: 29286.4, 300 sec: 28963.6). Total num frames: 12558336. Throughput: 0: 7321.9. Samples: 2121122. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:02:34,216][12851] Avg episode reward: [(0, '4.239')]
+[2025-04-03 14:02:34,740][20447] Updated weights for policy 0, policy_version 3070 (0.0010)
+[2025-04-03 14:02:36,100][20447] Updated weights for policy 0, policy_version 3080 (0.0010)
+[2025-04-03 14:02:37,551][20447] Updated weights for policy 0, policy_version 3090 (0.0010)
+[2025-04-03 14:02:38,932][20447] Updated weights for policy 0, policy_version 3100 (0.0010)
+[2025-04-03 14:02:39,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29286.3, 300 sec: 29005.2). Total num frames: 12701696. Throughput: 0: 7330.8. Samples: 2165338. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:39,217][12851] Avg episode reward: [(0, '4.375')]
+[2025-04-03 14:02:40,317][20447] Updated weights for policy 0, policy_version 3110 (0.0011)
+[2025-04-03 14:02:41,697][20447] Updated weights for policy 0, policy_version 3120 (0.0010)
+[2025-04-03 14:02:43,067][20447] Updated weights for policy 0, policy_version 3130 (0.0010)
+[2025-04-03 14:02:44,215][12851] Fps is (10 sec: 29491.2, 60 sec: 29354.7, 300 sec: 28991.4). Total num frames: 12853248. Throughput: 0: 7343.9. Samples: 2209752. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:44,216][12851] Avg episode reward: [(0, '4.398')]
+[2025-04-03 14:02:44,451][20447] Updated weights for policy 0, policy_version 3140 (0.0011)
+[2025-04-03 14:02:45,846][20447] Updated weights for policy 0, policy_version 3150 (0.0012)
+[2025-04-03 14:02:47,237][20447] Updated weights for policy 0, policy_version 3160 (0.0013)
+[2025-04-03 14:02:48,641][20447] Updated weights for policy 0, policy_version 3170 (0.0012)
+[2025-04-03 14:02:49,215][12851] Fps is (10 sec: 29900.7, 60 sec: 29354.6, 300 sec: 28977.4). Total num frames: 13000704. Throughput: 0: 7343.5. Samples: 2231828. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:49,217][12851] Avg episode reward: [(0, '4.477')]
+[2025-04-03 14:02:50,011][20447] Updated weights for policy 0, policy_version 3180 (0.0010)
+[2025-04-03 14:02:51,416][20447] Updated weights for policy 0, policy_version 3190 (0.0011)
+[2025-04-03 14:02:52,831][20447] Updated weights for policy 0, policy_version 3200 (0.0010)
+[2025-04-03 14:02:54,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29354.8, 300 sec: 28921.9). Total num frames: 13144064. Throughput: 0: 7345.4. Samples: 2275776. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:54,217][12851] Avg episode reward: [(0, '4.510')]
+[2025-04-03 14:02:54,221][20447] Updated weights for policy 0, policy_version 3210 (0.0010)
+[2025-04-03 14:02:55,667][20447] Updated weights for policy 0, policy_version 3220 (0.0012)
+[2025-04-03 14:02:57,045][20447] Updated weights for policy 0, policy_version 3230 (0.0010)
+[2025-04-03 14:02:58,490][20447] Updated weights for policy 0, policy_version 3240 (0.0012)
+[2025-04-03 14:02:59,215][12851] Fps is (10 sec: 29082.0, 60 sec: 29354.6, 300 sec: 28908.1). Total num frames: 13291520. Throughput: 0: 7336.7. Samples: 2319260. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:02:59,217][12851] Avg episode reward: [(0, '4.568')]
+[2025-04-03 14:02:59,899][20447] Updated weights for policy 0, policy_version 3250 (0.0012)
+[2025-04-03 14:03:01,347][20447] Updated weights for policy 0, policy_version 3260 (0.0010)
+[2025-04-03 14:03:02,767][20447] Updated weights for policy 0, policy_version 3270 (0.0010)
+[2025-04-03 14:03:04,175][20447] Updated weights for policy 0, policy_version 3280 (0.0009)
+[2025-04-03 14:03:04,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29286.4, 300 sec: 28866.4). Total num frames: 13434880. Throughput: 0: 7325.9. Samples: 2340720. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:04,216][12851] Avg episode reward: [(0, '4.302')]
+[2025-04-03 14:03:05,557][20447] Updated weights for policy 0, policy_version 3290 (0.0009)
+[2025-04-03 14:03:06,951][20447] Updated weights for policy 0, policy_version 3300 (0.0012)
+[2025-04-03 14:03:08,346][20447] Updated weights for policy 0, policy_version 3310 (0.0010)
+[2025-04-03 14:03:09,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29354.7, 300 sec: 28838.6). Total num frames: 13582336. Throughput: 0: 7320.4. Samples: 2384540. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:09,217][12851] Avg episode reward: [(0, '4.515')]
+[2025-04-03 14:03:09,751][20447] Updated weights for policy 0, policy_version 3320 (0.0010)
+[2025-04-03 14:03:11,145][20447] Updated weights for policy 0, policy_version 3330 (0.0009)
+[2025-04-03 14:03:12,556][20447] Updated weights for policy 0, policy_version 3340 (0.0011)
+[2025-04-03 14:03:13,967][20447] Updated weights for policy 0, policy_version 3350 (0.0011)
+[2025-04-03 14:03:14,215][12851] Fps is (10 sec: 29081.4, 60 sec: 29286.4, 300 sec: 28810.9). Total num frames: 13725696. Throughput: 0: 7316.7. Samples: 2428510. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:14,217][12851] Avg episode reward: [(0, '4.274')]
+[2025-04-03 14:03:15,332][20447] Updated weights for policy 0, policy_version 3360 (0.0010)
+[2025-04-03 14:03:16,742][20447] Updated weights for policy 0, policy_version 3370 (0.0011)
+[2025-04-03 14:03:18,155][20447] Updated weights for policy 0, policy_version 3380 (0.0010)
+[2025-04-03 14:03:19,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29286.4, 300 sec: 28824.7). Total num frames: 13873152. Throughput: 0: 7319.7. Samples: 2450508. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:19,216][12851] Avg episode reward: [(0, '4.384')]
+[2025-04-03 14:03:19,549][20447] Updated weights for policy 0, policy_version 3390 (0.0011)
+[2025-04-03 14:03:20,938][20447] Updated weights for policy 0, policy_version 3400 (0.0009)
+[2025-04-03 14:03:22,348][20447] Updated weights for policy 0, policy_version 3410 (0.0010)
+[2025-04-03 14:03:23,760][20447] Updated weights for policy 0, policy_version 3420 (0.0010)
+[2025-04-03 14:03:24,215][12851] Fps is (10 sec: 29491.7, 60 sec: 29286.4, 300 sec: 28838.6). Total num frames: 14020608. Throughput: 0: 7310.7. Samples: 2494318. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:24,217][12851] Avg episode reward: [(0, '4.498')]
+[2025-04-03 14:03:25,198][20447] Updated weights for policy 0, policy_version 3430 (0.0011)
+[2025-04-03 14:03:26,618][20447] Updated weights for policy 0, policy_version 3440 (0.0011)
+[2025-04-03 14:03:28,072][20447] Updated weights for policy 0, policy_version 3450 (0.0013)
+[2025-04-03 14:03:29,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29218.2, 300 sec: 28838.6). Total num frames: 14163968. Throughput: 0: 7279.6. Samples: 2537332. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:03:29,216][12851] Avg episode reward: [(0, '4.431')]
+[2025-04-03 14:03:29,221][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000003458_14163968.pth...
+[2025-04-03 14:03:29,345][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000001765_7229440.pth
+[2025-04-03 14:03:29,487][20447] Updated weights for policy 0, policy_version 3460 (0.0010)
+[2025-04-03 14:03:30,894][20447] Updated weights for policy 0, policy_version 3470 (0.0010)
+[2025-04-03 14:03:32,306][20447] Updated weights for policy 0, policy_version 3480 (0.0013)
+[2025-04-03 14:03:33,723][20447] Updated weights for policy 0, policy_version 3490 (0.0010)
+[2025-04-03 14:03:34,215][12851] Fps is (10 sec: 28671.6, 60 sec: 29149.8, 300 sec: 28824.7). Total num frames: 14307328. Throughput: 0: 7269.4. Samples: 2558950. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:03:34,217][12851] Avg episode reward: [(0, '4.481')]
+[2025-04-03 14:03:35,102][20447] Updated weights for policy 0, policy_version 3500 (0.0010)
+[2025-04-03 14:03:36,492][20447] Updated weights for policy 0, policy_version 3510 (0.0010)
+[2025-04-03 14:03:37,901][20447] Updated weights for policy 0, policy_version 3520 (0.0011)
+[2025-04-03 14:03:39,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29218.2, 300 sec: 28838.6). Total num frames: 14454784. Throughput: 0: 7270.9. Samples: 2602966. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:03:39,217][12851] Avg episode reward: [(0, '4.364')]
+[2025-04-03 14:03:39,333][20447] Updated weights for policy 0, policy_version 3530 (0.0011)
+[2025-04-03 14:03:40,767][20447] Updated weights for policy 0, policy_version 3540 (0.0009)
+[2025-04-03 14:03:42,161][20447] Updated weights for policy 0, policy_version 3550 (0.0009)
+[2025-04-03 14:03:43,550][20447] Updated weights for policy 0, policy_version 3560 (0.0011)
+[2025-04-03 14:03:44,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29081.5, 300 sec: 28838.6). Total num frames: 14598144. Throughput: 0: 7270.8. Samples: 2646448. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:03:44,217][12851] Avg episode reward: [(0, '4.380')]
+[2025-04-03 14:03:44,957][20447] Updated weights for policy 0, policy_version 3570 (0.0010)
+[2025-04-03 14:03:46,329][20447] Updated weights for policy 0, policy_version 3580 (0.0009)
+[2025-04-03 14:03:47,713][20447] Updated weights for policy 0, policy_version 3590 (0.0010)
+[2025-04-03 14:03:49,142][20447] Updated weights for policy 0, policy_version 3600 (0.0010)
+[2025-04-03 14:03:49,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29081.7, 300 sec: 28852.5). Total num frames: 14745600. Throughput: 0: 7286.9. Samples: 2668632. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:03:49,216][12851] Avg episode reward: [(0, '4.340')]
+[2025-04-03 14:03:50,558][20447] Updated weights for policy 0, policy_version 3610 (0.0011)
+[2025-04-03 14:03:51,936][20447] Updated weights for policy 0, policy_version 3620 (0.0010)
+[2025-04-03 14:03:53,371][20447] Updated weights for policy 0, policy_version 3630 (0.0011)
+[2025-04-03 14:03:54,215][12851] Fps is (10 sec: 29082.1, 60 sec: 29081.6, 300 sec: 28838.6). Total num frames: 14888960. Throughput: 0: 7278.9. Samples: 2712090. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:54,216][12851] Avg episode reward: [(0, '4.386')]
+[2025-04-03 14:03:54,769][20447] Updated weights for policy 0, policy_version 3640 (0.0010)
+[2025-04-03 14:03:56,177][20447] Updated weights for policy 0, policy_version 3650 (0.0010)
+[2025-04-03 14:03:57,595][20447] Updated weights for policy 0, policy_version 3660 (0.0010)
+[2025-04-03 14:03:59,010][20447] Updated weights for policy 0, policy_version 3670 (0.0011)
+[2025-04-03 14:03:59,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29081.6, 300 sec: 28866.4). Total num frames: 15036416. Throughput: 0: 7270.1. Samples: 2755662. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:03:59,217][12851] Avg episode reward: [(0, '4.456')]
+[2025-04-03 14:04:00,452][20447] Updated weights for policy 0, policy_version 3680 (0.0011)
+[2025-04-03 14:04:01,856][20447] Updated weights for policy 0, policy_version 3690 (0.0009)
+[2025-04-03 14:04:03,254][20447] Updated weights for policy 0, policy_version 3700 (0.0009)
+[2025-04-03 14:04:04,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29081.6, 300 sec: 28880.3). Total num frames: 15179776. Throughput: 0: 7262.4. Samples: 2777314. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:04:04,216][12851] Avg episode reward: [(0, '4.443')]
+[2025-04-03 14:04:04,658][20447] Updated weights for policy 0, policy_version 3710 (0.0011)
+[2025-04-03 14:04:06,050][20447] Updated weights for policy 0, policy_version 3720 (0.0008)
+[2025-04-03 14:04:07,439][20447] Updated weights for policy 0, policy_version 3730 (0.0011)
+[2025-04-03 14:04:08,868][20447] Updated weights for policy 0, policy_version 3740 (0.0011)
+[2025-04-03 14:04:09,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29081.6, 300 sec: 28894.2). Total num frames: 15327232. Throughput: 0: 7264.6. Samples: 2821224. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:04:09,216][12851] Avg episode reward: [(0, '4.387')]
+[2025-04-03 14:04:10,258][20447] Updated weights for policy 0, policy_version 3750 (0.0010)
+[2025-04-03 14:04:11,672][20447] Updated weights for policy 0, policy_version 3760 (0.0009)
+[2025-04-03 14:04:13,082][20447] Updated weights for policy 0, policy_version 3770 (0.0010)
+[2025-04-03 14:04:14,215][12851] Fps is (10 sec: 29491.4, 60 sec: 29150.0, 300 sec: 28921.9). Total num frames: 15474688. Throughput: 0: 7281.5. Samples: 2864998. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:04:14,216][12851] Avg episode reward: [(0, '4.285')]
+[2025-04-03 14:04:14,493][20447] Updated weights for policy 0, policy_version 3780 (0.0010)
+[2025-04-03 14:04:15,885][20447] Updated weights for policy 0, policy_version 3790 (0.0012)
+[2025-04-03 14:04:17,302][20447] Updated weights for policy 0, policy_version 3800 (0.0011)
+[2025-04-03 14:04:18,689][20447] Updated weights for policy 0, policy_version 3810 (0.0009)
+[2025-04-03 14:04:19,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29081.6, 300 sec: 28921.9). Total num frames: 15618048. Throughput: 0: 7282.7. Samples: 2886670. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:04:19,217][12851] Avg episode reward: [(0, '4.462')]
+[2025-04-03 14:04:20,127][20447] Updated weights for policy 0, policy_version 3820 (0.0011)
+[2025-04-03 14:04:21,541][20447] Updated weights for policy 0, policy_version 3830 (0.0010)
+[2025-04-03 14:04:22,951][20447] Updated weights for policy 0, policy_version 3840 (0.0009)
+[2025-04-03 14:04:24,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29081.6, 300 sec: 28935.8). Total num frames: 15765504. Throughput: 0: 7276.4. Samples: 2930404. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:04:24,217][12851] Avg episode reward: [(0, '4.632')]
+[2025-04-03 14:04:24,356][20447] Updated weights for policy 0, policy_version 3850 (0.0010)
+[2025-04-03 14:04:25,729][20447] Updated weights for policy 0, policy_version 3860 (0.0009)
+[2025-04-03 14:04:27,100][20447] Updated weights for policy 0, policy_version 3870 (0.0010)
+[2025-04-03 14:04:28,532][20447] Updated weights for policy 0, policy_version 3880 (0.0009)
+[2025-04-03 14:04:29,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29081.6, 300 sec: 28949.7). Total num frames: 15908864. Throughput: 0: 7284.9. Samples: 2974266. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:04:29,216][12851] Avg episode reward: [(0, '4.602')]
+[2025-04-03 14:04:29,957][20447] Updated weights for policy 0, policy_version 3890 (0.0010)
+[2025-04-03 14:04:31,330][20447] Updated weights for policy 0, policy_version 3900 (0.0011)
+[2025-04-03 14:04:32,765][20447] Updated weights for policy 0, policy_version 3910 (0.0009)
+[2025-04-03 14:04:34,130][20447] Updated weights for policy 0, policy_version 3920 (0.0009)
+[2025-04-03 14:04:34,215][12851] Fps is (10 sec: 29081.2, 60 sec: 29149.9, 300 sec: 28963.6). Total num frames: 16056320. Throughput: 0: 7276.8. Samples: 2996088. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:04:34,217][12851] Avg episode reward: [(0, '4.512')]
+[2025-04-03 14:04:35,506][20447] Updated weights for policy 0, policy_version 3930 (0.0010)
+[2025-04-03 14:04:36,926][20447] Updated weights for policy 0, policy_version 3940 (0.0011)
+[2025-04-03 14:04:38,323][20447] Updated weights for policy 0, policy_version 3950 (0.0010)
+[2025-04-03 14:04:39,215][12851] Fps is (10 sec: 29491.0, 60 sec: 29149.8, 300 sec: 28977.5). Total num frames: 16203776. Throughput: 0: 7289.8. Samples: 3040132. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:04:39,216][12851] Avg episode reward: [(0, '4.295')]
+[2025-04-03 14:04:39,727][20447] Updated weights for policy 0, policy_version 3960 (0.0010)
+[2025-04-03 14:04:41,188][20447] Updated weights for policy 0, policy_version 3970 (0.0010)
+[2025-04-03 14:04:42,572][20447] Updated weights for policy 0, policy_version 3980 (0.0011)
+[2025-04-03 14:04:43,961][20447] Updated weights for policy 0, policy_version 3990 (0.0009)
+[2025-04-03 14:04:44,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29150.0, 300 sec: 28991.4). Total num frames: 16347136. Throughput: 0: 7289.8. Samples: 3083702. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:04:44,216][12851] Avg episode reward: [(0, '4.535')]
+[2025-04-03 14:04:45,366][20447] Updated weights for policy 0, policy_version 4000 (0.0009)
+[2025-04-03 14:04:46,772][20447] Updated weights for policy 0, policy_version 4010 (0.0011)
+[2025-04-03 14:04:48,191][20447] Updated weights for policy 0, policy_version 4020 (0.0011)
+[2025-04-03 14:04:49,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29149.8, 300 sec: 29005.2). Total num frames: 16494592. Throughput: 0: 7290.7. Samples: 3105396. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:04:49,217][12851] Avg episode reward: [(0, '4.389')]
+[2025-04-03 14:04:49,599][20447] Updated weights for policy 0, policy_version 4030 (0.0011)
+[2025-04-03 14:04:51,035][20447] Updated weights for policy 0, policy_version 4040 (0.0010)
+[2025-04-03 14:04:52,426][20447] Updated weights for policy 0, policy_version 4050 (0.0009)
+[2025-04-03 14:04:53,826][20447] Updated weights for policy 0, policy_version 4060 (0.0011)
+[2025-04-03 14:04:54,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29149.8, 300 sec: 29005.2). Total num frames: 16637952. Throughput: 0: 7284.2. Samples: 3149016. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:04:54,217][12851] Avg episode reward: [(0, '4.644')]
+[2025-04-03 14:04:55,223][20447] Updated weights for policy 0, policy_version 4070 (0.0010)
+[2025-04-03 14:04:56,624][20447] Updated weights for policy 0, policy_version 4080 (0.0010)
+[2025-04-03 14:04:57,997][20447] Updated weights for policy 0, policy_version 4090 (0.0010)
+[2025-04-03 14:04:59,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29149.9, 300 sec: 29019.1). Total num frames: 16785408. Throughput: 0: 7289.6. Samples: 3193032. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:04:59,217][12851] Avg episode reward: [(0, '4.273')]
+[2025-04-03 14:04:59,444][20447] Updated weights for policy 0, policy_version 4100 (0.0010)
+[2025-04-03 14:05:00,853][20447] Updated weights for policy 0, policy_version 4110 (0.0009)
+[2025-04-03 14:05:02,255][20447] Updated weights for policy 0, policy_version 4120 (0.0010)
+[2025-04-03 14:05:03,646][20447] Updated weights for policy 0, policy_version 4130 (0.0009)
+[2025-04-03 14:05:04,215][12851] Fps is (10 sec: 29491.5, 60 sec: 29218.1, 300 sec: 29019.1). Total num frames: 16932864. Throughput: 0: 7289.3. Samples: 3214690. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:05:04,216][12851] Avg episode reward: [(0, '4.467')]
+[2025-04-03 14:05:05,055][20447] Updated weights for policy 0, policy_version 4140 (0.0010)
+[2025-04-03 14:05:06,446][20447] Updated weights for policy 0, policy_version 4150 (0.0011)
+[2025-04-03 14:05:07,842][20447] Updated weights for policy 0, policy_version 4160 (0.0009)
+[2025-04-03 14:05:09,215][12851] Fps is (10 sec: 29081.7, 60 sec: 29149.9, 300 sec: 29019.1). Total num frames: 17076224. Throughput: 0: 7292.2. Samples: 3258554. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:05:09,216][12851] Avg episode reward: [(0, '4.505')]
+[2025-04-03 14:05:09,268][20447] Updated weights for policy 0, policy_version 4170 (0.0009)
+[2025-04-03 14:05:10,661][20447] Updated weights for policy 0, policy_version 4180 (0.0012)
+[2025-04-03 14:05:12,053][20447] Updated weights for policy 0, policy_version 4190 (0.0011)
+[2025-04-03 14:05:13,457][20447] Updated weights for policy 0, policy_version 4200 (0.0011)
+[2025-04-03 14:05:14,215][12851] Fps is (10 sec: 29081.1, 60 sec: 29149.8, 300 sec: 29033.0). Total num frames: 17223680. Throughput: 0: 7294.0. Samples: 3302496. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:05:14,217][12851] Avg episode reward: [(0, '4.257')]
+[2025-04-03 14:05:14,850][20447] Updated weights for policy 0, policy_version 4210 (0.0009)
+[2025-04-03 14:05:16,275][20447] Updated weights for policy 0, policy_version 4220 (0.0010)
+[2025-04-03 14:05:17,684][20447] Updated weights for policy 0, policy_version 4230 (0.0010)
+[2025-04-03 14:05:19,081][20447] Updated weights for policy 0, policy_version 4240 (0.0010)
+[2025-04-03 14:05:19,215][12851] Fps is (10 sec: 29491.1, 60 sec: 29218.1, 300 sec: 29046.9). Total num frames: 17371136. Throughput: 0: 7296.2. Samples: 3324416. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:05:19,216][12851] Avg episode reward: [(0, '4.325')]
+[2025-04-03 14:05:20,513][20447] Updated weights for policy 0, policy_version 4250 (0.0011)
+[2025-04-03 14:05:21,879][20447] Updated weights for policy 0, policy_version 4260 (0.0009)
+[2025-04-03 14:05:23,302][20447] Updated weights for policy 0, policy_version 4270 (0.0010)
+[2025-04-03 14:05:24,216][12851] Fps is (10 sec: 29080.8, 60 sec: 29149.6, 300 sec: 29046.8). Total num frames: 17514496. Throughput: 0: 7285.1. Samples: 3367962. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:05:24,217][12851] Avg episode reward: [(0, '4.489')]
+[2025-04-03 14:05:24,689][20447] Updated weights for policy 0, policy_version 4280 (0.0010)
+[2025-04-03 14:05:26,151][20447] Updated weights for policy 0, policy_version 4290 (0.0009)
+[2025-04-03 14:05:27,617][20447] Updated weights for policy 0, policy_version 4300 (0.0010)
+[2025-04-03 14:05:29,015][20447] Updated weights for policy 0, policy_version 4310 (0.0009)
+[2025-04-03 14:05:29,215][12851] Fps is (10 sec: 28671.5, 60 sec: 29149.8, 300 sec: 29046.9). Total num frames: 17657856. Throughput: 0: 7275.1. Samples: 3411082. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:05:29,217][12851] Avg episode reward: [(0, '4.506')]
+[2025-04-03 14:05:29,224][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000004311_17657856.pth...
+[2025-04-03 14:05:29,341][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000002602_10657792.pth
+[2025-04-03 14:05:30,434][20447] Updated weights for policy 0, policy_version 4320 (0.0010)
+[2025-04-03 14:05:31,810][20447] Updated weights for policy 0, policy_version 4330 (0.0009)
+[2025-04-03 14:05:33,187][20447] Updated weights for policy 0, policy_version 4340 (0.0009)
+[2025-04-03 14:05:34,220][12851] Fps is (10 sec: 29069.0, 60 sec: 29147.6, 300 sec: 29060.3). Total num frames: 17805312. Throughput: 0: 7280.7. Samples: 3433060. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:05:34,222][12851] Avg episode reward: [(0, '4.515')]
+[2025-04-03 14:05:34,604][20447] Updated weights for policy 0, policy_version 4350 (0.0010)
+[2025-04-03 14:05:36,053][20447] Updated weights for policy 0, policy_version 4360 (0.0009)
+[2025-04-03 14:05:37,432][20447] Updated weights for policy 0, policy_version 4370 (0.0010)
+[2025-04-03 14:05:38,874][20447] Updated weights for policy 0, policy_version 4380 (0.0009)
+[2025-04-03 14:05:39,215][12851] Fps is (10 sec: 29082.1, 60 sec: 29081.6, 300 sec: 29060.8). Total num frames: 17948672. Throughput: 0: 7280.8. Samples: 3476650. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:05:39,217][12851] Avg episode reward: [(0, '4.411')]
+[2025-04-03 14:05:40,248][20447] Updated weights for policy 0, policy_version 4390 (0.0012)
+[2025-04-03 14:05:41,620][20447] Updated weights for policy 0, policy_version 4400 (0.0010)
+[2025-04-03 14:05:42,974][20447] Updated weights for policy 0, policy_version 4410 (0.0010)
+[2025-04-03 14:05:44,215][12851] Fps is (10 sec: 29095.3, 60 sec: 29149.8, 300 sec: 29088.5). Total num frames: 18096128. Throughput: 0: 7279.8. Samples: 3520624. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:05:44,217][12851] Avg episode reward: [(0, '4.460')]
+[2025-04-03 14:05:44,427][20447] Updated weights for policy 0, policy_version 4420 (0.0010)
+[2025-04-03 14:05:45,866][20447] Updated weights for policy 0, policy_version 4430 (0.0010)
+[2025-04-03 14:05:47,236][20447] Updated weights for policy 0, policy_version 4440 (0.0011)
+[2025-04-03 14:05:48,668][20447] Updated weights for policy 0, policy_version 4450 (0.0010)
+[2025-04-03 14:05:49,215][12851] Fps is (10 sec: 29491.2, 60 sec: 29149.9, 300 sec: 29130.2). Total num frames: 18243584. Throughput: 0: 7284.0. Samples: 3542472. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:05:49,217][12851] Avg episode reward: [(0, '4.468')]
+[2025-04-03 14:05:50,071][20447] Updated weights for policy 0, policy_version 4460 (0.0010)
+[2025-04-03 14:05:51,500][20447] Updated weights for policy 0, policy_version 4470 (0.0011)
+[2025-04-03 14:05:52,996][20447] Updated weights for policy 0, policy_version 4480 (0.0012)
+[2025-04-03 14:05:54,215][12851] Fps is (10 sec: 28671.8, 60 sec: 29081.6, 300 sec: 29116.3). Total num frames: 18382848. Throughput: 0: 7261.9. Samples: 3585342. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:05:54,217][12851] Avg episode reward: [(0, '4.474')]
+[2025-04-03 14:05:54,462][20447] Updated weights for policy 0, policy_version 4490 (0.0010)
+[2025-04-03 14:05:55,921][20447] Updated weights for policy 0, policy_version 4500 (0.0011)
+[2025-04-03 14:05:57,334][20447] Updated weights for policy 0, policy_version 4510 (0.0010)
+[2025-04-03 14:05:58,726][20447] Updated weights for policy 0, policy_version 4520 (0.0010)
+[2025-04-03 14:05:59,215][12851] Fps is (10 sec: 28262.3, 60 sec: 29013.3, 300 sec: 29116.3). Total num frames: 18526208. Throughput: 0: 7236.1. Samples: 3628118. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:05:59,217][12851] Avg episode reward: [(0, '4.608')]
+[2025-04-03 14:06:00,136][20447] Updated weights for policy 0, policy_version 4530 (0.0010)
+[2025-04-03 14:06:01,610][20447] Updated weights for policy 0, policy_version 4540 (0.0009)
+[2025-04-03 14:06:03,059][20447] Updated weights for policy 0, policy_version 4550 (0.0011)
+[2025-04-03 14:06:04,215][12851] Fps is (10 sec: 28262.5, 60 sec: 28876.8, 300 sec: 29102.4). Total num frames: 18665472. Throughput: 0: 7221.5. Samples: 3649382. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:06:04,216][12851] Avg episode reward: [(0, '4.483')]
+[2025-04-03 14:06:04,539][20447] Updated weights for policy 0, policy_version 4560 (0.0011)
+[2025-04-03 14:06:05,958][20447] Updated weights for policy 0, policy_version 4570 (0.0010)
+[2025-04-03 14:06:07,327][20447] Updated weights for policy 0, policy_version 4580 (0.0011)
+[2025-04-03 14:06:08,732][20447] Updated weights for policy 0, policy_version 4590 (0.0010)
+[2025-04-03 14:06:09,215][12851] Fps is (10 sec: 28671.6, 60 sec: 28945.0, 300 sec: 29116.3). Total num frames: 18812928. Throughput: 0: 7209.0. Samples: 3692366. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:06:09,217][12851] Avg episode reward: [(0, '4.418')]
+[2025-04-03 14:06:10,124][20447] Updated weights for policy 0, policy_version 4600 (0.0010)
+[2025-04-03 14:06:11,530][20447] Updated weights for policy 0, policy_version 4610 (0.0010)
+[2025-04-03 14:06:12,944][20447] Updated weights for policy 0, policy_version 4620 (0.0012)
+[2025-04-03 14:06:14,215][12851] Fps is (10 sec: 29491.4, 60 sec: 28945.1, 300 sec: 29116.3). Total num frames: 18960384. Throughput: 0: 7234.6. Samples: 3736636. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:06:14,216][12851] Avg episode reward: [(0, '4.636')]
+[2025-04-03 14:06:14,311][20447] Updated weights for policy 0, policy_version 4630 (0.0011)
+[2025-04-03 14:06:15,691][20447] Updated weights for policy 0, policy_version 4640 (0.0010)
+[2025-04-03 14:06:17,077][20447] Updated weights for policy 0, policy_version 4650 (0.0011)
+[2025-04-03 14:06:18,530][20447] Updated weights for policy 0, policy_version 4660 (0.0011)
+[2025-04-03 14:06:19,215][12851] Fps is (10 sec: 29081.9, 60 sec: 28876.8, 300 sec: 29116.3). Total num frames: 19103744. Throughput: 0: 7234.4. Samples: 3758572. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:06:19,217][12851] Avg episode reward: [(0, '4.330')]
+[2025-04-03 14:06:19,911][20447] Updated weights for policy 0, policy_version 4670 (0.0012)
+[2025-04-03 14:06:21,313][20447] Updated weights for policy 0, policy_version 4680 (0.0013)
+[2025-04-03 14:06:22,726][20447] Updated weights for policy 0, policy_version 4690 (0.0012)
+[2025-04-03 14:06:24,100][20447] Updated weights for policy 0, policy_version 4700 (0.0011)
+[2025-04-03 14:06:24,215][12851] Fps is (10 sec: 29081.3, 60 sec: 28945.2, 300 sec: 29130.2). Total num frames: 19251200. Throughput: 0: 7239.2. Samples: 3802416. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:06:24,216][12851] Avg episode reward: [(0, '4.240')]
+[2025-04-03 14:06:25,503][20447] Updated weights for policy 0, policy_version 4710 (0.0010)
+[2025-04-03 14:06:26,967][20447] Updated weights for policy 0, policy_version 4720 (0.0011)
+[2025-04-03 14:06:28,377][20447] Updated weights for policy 0, policy_version 4730 (0.0010)
+[2025-04-03 14:06:29,215][12851] Fps is (10 sec: 29491.5, 60 sec: 29013.5, 300 sec: 29144.1). Total num frames: 19398656. Throughput: 0: 7227.8. Samples: 3845876. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:06:29,216][12851] Avg episode reward: [(0, '4.448')]
+[2025-04-03 14:06:29,771][20447] Updated weights for policy 0, policy_version 4740 (0.0012)
+[2025-04-03 14:06:31,190][20447] Updated weights for policy 0, policy_version 4750 (0.0012)
+[2025-04-03 14:06:32,545][20447] Updated weights for policy 0, policy_version 4760 (0.0010)
+[2025-04-03 14:06:33,931][20447] Updated weights for policy 0, policy_version 4770 (0.0011)
+[2025-04-03 14:06:34,215][12851] Fps is (10 sec: 29081.9, 60 sec: 28947.4, 300 sec: 29144.1). Total num frames: 19542016. Throughput: 0: 7230.4. Samples: 3867840. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:06:34,216][12851] Avg episode reward: [(0, '4.569')]
+[2025-04-03 14:06:35,345][20447] Updated weights for policy 0, policy_version 4780 (0.0011)
+[2025-04-03 14:06:36,781][20447] Updated weights for policy 0, policy_version 4790 (0.0011)
+[2025-04-03 14:06:38,165][20447] Updated weights for policy 0, policy_version 4800 (0.0010)
+[2025-04-03 14:06:39,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29013.3, 300 sec: 29144.1). Total num frames: 19689472. Throughput: 0: 7257.3. Samples: 3911922. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:06:39,216][12851] Avg episode reward: [(0, '4.273')]
+[2025-04-03 14:06:39,533][20447] Updated weights for policy 0, policy_version 4810 (0.0011)
+[2025-04-03 14:06:40,948][20447] Updated weights for policy 0, policy_version 4820 (0.0012)
+[2025-04-03 14:06:42,352][20447] Updated weights for policy 0, policy_version 4830 (0.0010)
+[2025-04-03 14:06:43,738][20447] Updated weights for policy 0, policy_version 4840 (0.0009)
+[2025-04-03 14:06:44,216][12851] Fps is (10 sec: 29489.7, 60 sec: 29013.1, 300 sec: 29144.0). Total num frames: 19836928. Throughput: 0: 7275.9. Samples: 3955536. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:06:44,217][12851] Avg episode reward: [(0, '4.474')]
+[2025-04-03 14:06:45,172][20447] Updated weights for policy 0, policy_version 4850 (0.0011)
+[2025-04-03 14:06:46,590][20447] Updated weights for policy 0, policy_version 4860 (0.0011)
+[2025-04-03 14:06:47,987][20447] Updated weights for policy 0, policy_version 4870 (0.0008)
+[2025-04-03 14:06:49,215][12851] Fps is (10 sec: 29491.1, 60 sec: 29013.3, 300 sec: 29158.0). Total num frames: 19984384. Throughput: 0: 7291.1. Samples: 3977482. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:06:49,217][12851] Avg episode reward: [(0, '4.448')]
+[2025-04-03 14:06:49,375][20447] Updated weights for policy 0, policy_version 4880 (0.0010)
+[2025-04-03 14:06:50,776][20447] Updated weights for policy 0, policy_version 4890 (0.0011)
+[2025-04-03 14:06:52,155][20447] Updated weights for policy 0, policy_version 4900 (0.0009)
+[2025-04-03 14:06:53,572][20447] Updated weights for policy 0, policy_version 4910 (0.0011)
+[2025-04-03 14:06:54,215][12851] Fps is (10 sec: 29082.9, 60 sec: 29081.6, 300 sec: 29144.1). Total num frames: 20127744. Throughput: 0: 7307.3. Samples: 4021192. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:06:54,216][12851] Avg episode reward: [(0, '4.353')]
+[2025-04-03 14:06:55,020][20447] Updated weights for policy 0, policy_version 4920 (0.0011)
+[2025-04-03 14:06:56,457][20447] Updated weights for policy 0, policy_version 4930 (0.0010)
+[2025-04-03 14:06:57,870][20447] Updated weights for policy 0, policy_version 4940 (0.0011)
+[2025-04-03 14:06:59,215][12851] Fps is (10 sec: 28672.2, 60 sec: 29081.6, 300 sec: 29130.2). Total num frames: 20271104. Throughput: 0: 7286.8. Samples: 4064542. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:06:59,217][12851] Avg episode reward: [(0, '4.407')]
+[2025-04-03 14:06:59,270][20447] Updated weights for policy 0, policy_version 4950 (0.0009)
+[2025-04-03 14:07:00,666][20447] Updated weights for policy 0, policy_version 4960 (0.0012)
+[2025-04-03 14:07:02,068][20447] Updated weights for policy 0, policy_version 4970 (0.0011)
+[2025-04-03 14:07:03,457][20447] Updated weights for policy 0, policy_version 4980 (0.0011)
+[2025-04-03 14:07:04,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29218.2, 300 sec: 29144.1). Total num frames: 20418560. Throughput: 0: 7285.8. Samples: 4086434. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:04,216][12851] Avg episode reward: [(0, '4.315')]
+[2025-04-03 14:07:04,950][20447] Updated weights for policy 0, policy_version 4990 (0.0011)
+[2025-04-03 14:07:06,366][20447] Updated weights for policy 0, policy_version 5000 (0.0010)
+[2025-04-03 14:07:07,796][20447] Updated weights for policy 0, policy_version 5010 (0.0010)
+[2025-04-03 14:07:09,163][20447] Updated weights for policy 0, policy_version 5020 (0.0010)
+[2025-04-03 14:07:09,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29149.9, 300 sec: 29130.2). Total num frames: 20561920. Throughput: 0: 7269.9. Samples: 4129560. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:07:09,216][12851] Avg episode reward: [(0, '4.428')]
+[2025-04-03 14:07:10,593][20447] Updated weights for policy 0, policy_version 5030 (0.0010)
+[2025-04-03 14:07:12,004][20447] Updated weights for policy 0, policy_version 5040 (0.0011)
+[2025-04-03 14:07:13,448][20447] Updated weights for policy 0, policy_version 5050 (0.0010)
+[2025-04-03 14:07:14,215][12851] Fps is (10 sec: 28672.1, 60 sec: 29081.6, 300 sec: 29116.3). Total num frames: 20705280. Throughput: 0: 7268.0. Samples: 4172934. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:14,217][12851] Avg episode reward: [(0, '4.356')]
+[2025-04-03 14:07:14,868][20447] Updated weights for policy 0, policy_version 5060 (0.0008)
+[2025-04-03 14:07:16,255][20447] Updated weights for policy 0, policy_version 5070 (0.0011)
+[2025-04-03 14:07:17,659][20447] Updated weights for policy 0, policy_version 5080 (0.0009)
+[2025-04-03 14:07:19,084][20447] Updated weights for policy 0, policy_version 5090 (0.0011)
+[2025-04-03 14:07:19,215][12851] Fps is (10 sec: 28672.1, 60 sec: 29081.6, 300 sec: 29102.4). Total num frames: 20848640. Throughput: 0: 7267.9. Samples: 4194896. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:07:19,216][12851] Avg episode reward: [(0, '4.340')]
+[2025-04-03 14:07:20,505][20447] Updated weights for policy 0, policy_version 5100 (0.0010)
+[2025-04-03 14:07:21,944][20447] Updated weights for policy 0, policy_version 5110 (0.0010)
+[2025-04-03 14:07:23,383][20447] Updated weights for policy 0, policy_version 5120 (0.0010)
+[2025-04-03 14:07:24,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29081.6, 300 sec: 29102.4). Total num frames: 20996096. Throughput: 0: 7246.0. Samples: 4237994. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:07:24,217][12851] Avg episode reward: [(0, '4.302')]
+[2025-04-03 14:07:24,752][20447] Updated weights for policy 0, policy_version 5130 (0.0009)
+[2025-04-03 14:07:26,142][20447] Updated weights for policy 0, policy_version 5140 (0.0009)
+[2025-04-03 14:07:27,556][20447] Updated weights for policy 0, policy_version 5150 (0.0010)
+[2025-04-03 14:07:28,944][20447] Updated weights for policy 0, policy_version 5160 (0.0010)
+[2025-04-03 14:07:29,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29013.3, 300 sec: 29088.5). Total num frames: 21139456. Throughput: 0: 7253.1. Samples: 4281920. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:29,217][12851] Avg episode reward: [(0, '4.214')]
+[2025-04-03 14:07:29,226][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000005162_21143552.pth...
+[2025-04-03 14:07:29,340][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000003458_14163968.pth
+[2025-04-03 14:07:30,333][20447] Updated weights for policy 0, policy_version 5170 (0.0010)
+[2025-04-03 14:07:31,730][20447] Updated weights for policy 0, policy_version 5180 (0.0010)
+[2025-04-03 14:07:33,227][20447] Updated weights for policy 0, policy_version 5190 (0.0012)
+[2025-04-03 14:07:34,216][12851] Fps is (10 sec: 28671.4, 60 sec: 29013.2, 300 sec: 29088.5). Total num frames: 21282816. Throughput: 0: 7251.7. Samples: 4303808. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:07:34,217][12851] Avg episode reward: [(0, '4.590')]
+[2025-04-03 14:07:34,671][20447] Updated weights for policy 0, policy_version 5200 (0.0011)
+[2025-04-03 14:07:36,078][20447] Updated weights for policy 0, policy_version 5210 (0.0010)
+[2025-04-03 14:07:37,462][20447] Updated weights for policy 0, policy_version 5220 (0.0011)
+[2025-04-03 14:07:38,835][20447] Updated weights for policy 0, policy_version 5230 (0.0010)
+[2025-04-03 14:07:39,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29013.3, 300 sec: 29074.7). Total num frames: 21430272. Throughput: 0: 7240.1. Samples: 4346996. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:07:39,217][12851] Avg episode reward: [(0, '4.348')]
+[2025-04-03 14:07:40,250][20447] Updated weights for policy 0, policy_version 5240 (0.0010)
+[2025-04-03 14:07:41,678][20447] Updated weights for policy 0, policy_version 5250 (0.0013)
+[2025-04-03 14:07:43,067][20447] Updated weights for policy 0, policy_version 5260 (0.0011)
+[2025-04-03 14:07:44,215][12851] Fps is (10 sec: 29491.9, 60 sec: 29013.6, 300 sec: 29074.7). Total num frames: 21577728. Throughput: 0: 7250.0. Samples: 4390792. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:44,217][12851] Avg episode reward: [(0, '4.447')]
+[2025-04-03 14:07:44,485][20447] Updated weights for policy 0, policy_version 5270 (0.0011)
+[2025-04-03 14:07:45,916][20447] Updated weights for policy 0, policy_version 5280 (0.0012)
+[2025-04-03 14:07:47,301][20447] Updated weights for policy 0, policy_version 5290 (0.0012)
+[2025-04-03 14:07:48,701][20447] Updated weights for policy 0, policy_version 5300 (0.0010)
+[2025-04-03 14:07:49,215][12851] Fps is (10 sec: 29081.6, 60 sec: 28945.1, 300 sec: 29074.7). Total num frames: 21721088. Throughput: 0: 7246.7. Samples: 4412536. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:49,217][12851] Avg episode reward: [(0, '4.500')]
+[2025-04-03 14:07:50,119][20447] Updated weights for policy 0, policy_version 5310 (0.0010)
+[2025-04-03 14:07:51,519][20447] Updated weights for policy 0, policy_version 5320 (0.0009)
+[2025-04-03 14:07:52,927][20447] Updated weights for policy 0, policy_version 5330 (0.0010)
+[2025-04-03 14:07:54,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29013.4, 300 sec: 29074.7). Total num frames: 21868544. Throughput: 0: 7258.1. Samples: 4456172. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:07:54,216][12851] Avg episode reward: [(0, '4.590')]
+[2025-04-03 14:07:54,344][20447] Updated weights for policy 0, policy_version 5340 (0.0009)
+[2025-04-03 14:07:55,777][20447] Updated weights for policy 0, policy_version 5350 (0.0012)
+[2025-04-03 14:07:57,176][20447] Updated weights for policy 0, policy_version 5360 (0.0009)
+[2025-04-03 14:07:58,568][20447] Updated weights for policy 0, policy_version 5370 (0.0011)
+[2025-04-03 14:07:59,216][12851] Fps is (10 sec: 29081.0, 60 sec: 29013.2, 300 sec: 29074.6). Total num frames: 22011904. Throughput: 0: 7258.8. Samples: 4499584. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:07:59,216][12851] Avg episode reward: [(0, '4.336')]
+[2025-04-03 14:07:59,953][20447] Updated weights for policy 0, policy_version 5380 (0.0009)
+[2025-04-03 14:08:01,367][20447] Updated weights for policy 0, policy_version 5390 (0.0011)
+[2025-04-03 14:08:02,757][20447] Updated weights for policy 0, policy_version 5400 (0.0011)
+[2025-04-03 14:08:04,161][20447] Updated weights for policy 0, policy_version 5410 (0.0011)
+[2025-04-03 14:08:04,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29013.3, 300 sec: 29074.7). Total num frames: 22159360. Throughput: 0: 7266.9. Samples: 4521904. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:04,216][12851] Avg episode reward: [(0, '4.410')]
+[2025-04-03 14:08:05,571][20447] Updated weights for policy 0, policy_version 5420 (0.0010)
+[2025-04-03 14:08:06,965][20447] Updated weights for policy 0, policy_version 5430 (0.0010)
+[2025-04-03 14:08:08,398][20447] Updated weights for policy 0, policy_version 5440 (0.0011)
+[2025-04-03 14:08:09,215][12851] Fps is (10 sec: 29082.0, 60 sec: 29013.3, 300 sec: 29074.7). Total num frames: 22302720. Throughput: 0: 7274.1. Samples: 4565330. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:08:09,216][12851] Avg episode reward: [(0, '4.454')]
+[2025-04-03 14:08:09,809][20447] Updated weights for policy 0, policy_version 5450 (0.0011)
+[2025-04-03 14:08:11,225][20447] Updated weights for policy 0, policy_version 5460 (0.0010)
+[2025-04-03 14:08:12,621][20447] Updated weights for policy 0, policy_version 5470 (0.0010)
+[2025-04-03 14:08:14,021][20447] Updated weights for policy 0, policy_version 5480 (0.0010)
+[2025-04-03 14:08:14,215][12851] Fps is (10 sec: 29081.4, 60 sec: 29081.5, 300 sec: 29074.7). Total num frames: 22450176. Throughput: 0: 7269.6. Samples: 4609052. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:08:14,216][12851] Avg episode reward: [(0, '4.289')]
+[2025-04-03 14:08:15,424][20447] Updated weights for policy 0, policy_version 5490 (0.0008)
+[2025-04-03 14:08:16,826][20447] Updated weights for policy 0, policy_version 5500 (0.0010)
+[2025-04-03 14:08:18,212][20447] Updated weights for policy 0, policy_version 5510 (0.0010)
+[2025-04-03 14:08:19,215][12851] Fps is (10 sec: 29491.6, 60 sec: 29149.9, 300 sec: 29074.7). Total num frames: 22597632. Throughput: 0: 7270.8. Samples: 4630994. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:08:19,216][12851] Avg episode reward: [(0, '4.431')]
+[2025-04-03 14:08:19,639][20447] Updated weights for policy 0, policy_version 5520 (0.0011)
+[2025-04-03 14:08:21,022][20447] Updated weights for policy 0, policy_version 5530 (0.0010)
+[2025-04-03 14:08:22,442][20447] Updated weights for policy 0, policy_version 5540 (0.0011)
+[2025-04-03 14:08:23,845][20447] Updated weights for policy 0, policy_version 5550 (0.0009)
+[2025-04-03 14:08:24,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29081.6, 300 sec: 29074.7). Total num frames: 22740992. Throughput: 0: 7285.7. Samples: 4674854. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:24,216][12851] Avg episode reward: [(0, '4.367')]
+[2025-04-03 14:08:25,264][20447] Updated weights for policy 0, policy_version 5560 (0.0010)
+[2025-04-03 14:08:26,671][20447] Updated weights for policy 0, policy_version 5570 (0.0010)
+[2025-04-03 14:08:28,115][20447] Updated weights for policy 0, policy_version 5580 (0.0012)
+[2025-04-03 14:08:29,215][12851] Fps is (10 sec: 28671.7, 60 sec: 29081.6, 300 sec: 29074.7). Total num frames: 22884352. Throughput: 0: 7268.5. Samples: 4717876. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:08:29,217][12851] Avg episode reward: [(0, '4.607')]
+[2025-04-03 14:08:29,554][20447] Updated weights for policy 0, policy_version 5590 (0.0009)
+[2025-04-03 14:08:30,983][20447] Updated weights for policy 0, policy_version 5600 (0.0012)
+[2025-04-03 14:08:32,380][20447] Updated weights for policy 0, policy_version 5610 (0.0009)
+[2025-04-03 14:08:33,808][20447] Updated weights for policy 0, policy_version 5620 (0.0009)
+[2025-04-03 14:08:34,215][12851] Fps is (10 sec: 28672.1, 60 sec: 29081.7, 300 sec: 29060.8). Total num frames: 23027712. Throughput: 0: 7268.1. Samples: 4739598. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:08:34,216][12851] Avg episode reward: [(0, '4.366')]
+[2025-04-03 14:08:35,218][20447] Updated weights for policy 0, policy_version 5630 (0.0009)
+[2025-04-03 14:08:36,625][20447] Updated weights for policy 0, policy_version 5640 (0.0010)
+[2025-04-03 14:08:38,042][20447] Updated weights for policy 0, policy_version 5650 (0.0009)
+[2025-04-03 14:08:39,215][12851] Fps is (10 sec: 29081.7, 60 sec: 29081.6, 300 sec: 29074.7). Total num frames: 23175168. Throughput: 0: 7263.2. Samples: 4783016. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:39,216][12851] Avg episode reward: [(0, '4.550')]
+[2025-04-03 14:08:39,496][20447] Updated weights for policy 0, policy_version 5660 (0.0011)
+[2025-04-03 14:08:40,911][20447] Updated weights for policy 0, policy_version 5670 (0.0010)
+[2025-04-03 14:08:42,290][20447] Updated weights for policy 0, policy_version 5680 (0.0009)
+[2025-04-03 14:08:43,722][20447] Updated weights for policy 0, policy_version 5690 (0.0010)
+[2025-04-03 14:08:44,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29013.4, 300 sec: 29060.8). Total num frames: 23318528. Throughput: 0: 7260.8. Samples: 4826318. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:44,216][12851] Avg episode reward: [(0, '4.354')]
+[2025-04-03 14:08:45,112][20447] Updated weights for policy 0, policy_version 5700 (0.0011)
+[2025-04-03 14:08:46,516][20447] Updated weights for policy 0, policy_version 5710 (0.0008)
+[2025-04-03 14:08:47,916][20447] Updated weights for policy 0, policy_version 5720 (0.0010)
+[2025-04-03 14:08:49,215][12851] Fps is (10 sec: 28672.0, 60 sec: 29013.3, 300 sec: 29060.8). Total num frames: 23461888. Throughput: 0: 7250.7. Samples: 4848184. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:08:49,216][12851] Avg episode reward: [(0, '4.421')]
+[2025-04-03 14:08:49,363][20447] Updated weights for policy 0, policy_version 5730 (0.0010)
+[2025-04-03 14:08:50,765][20447] Updated weights for policy 0, policy_version 5740 (0.0012)
+[2025-04-03 14:08:52,193][20447] Updated weights for policy 0, policy_version 5750 (0.0011)
+[2025-04-03 14:08:53,615][20447] Updated weights for policy 0, policy_version 5760 (0.0010)
+[2025-04-03 14:08:54,215][12851] Fps is (10 sec: 29081.7, 60 sec: 29013.3, 300 sec: 29060.8). Total num frames: 23609344. Throughput: 0: 7249.7. Samples: 4891564. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:54,216][12851] Avg episode reward: [(0, '4.519')]
+[2025-04-03 14:08:55,008][20447] Updated weights for policy 0, policy_version 5770 (0.0009)
+[2025-04-03 14:08:56,442][20447] Updated weights for policy 0, policy_version 5780 (0.0010)
+[2025-04-03 14:08:57,839][20447] Updated weights for policy 0, policy_version 5790 (0.0010)
+[2025-04-03 14:08:59,215][12851] Fps is (10 sec: 29081.7, 60 sec: 29013.5, 300 sec: 29060.8). Total num frames: 23752704. Throughput: 0: 7249.0. Samples: 4935258. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:08:59,216][12851] Avg episode reward: [(0, '4.533')]
+[2025-04-03 14:08:59,232][20447] Updated weights for policy 0, policy_version 5800 (0.0009)
+[2025-04-03 14:09:00,622][20447] Updated weights for policy 0, policy_version 5810 (0.0010)
+[2025-04-03 14:09:02,027][20447] Updated weights for policy 0, policy_version 5820 (0.0010)
+[2025-04-03 14:09:03,415][20447] Updated weights for policy 0, policy_version 5830 (0.0008)
+[2025-04-03 14:09:04,215][12851] Fps is (10 sec: 29080.9, 60 sec: 29013.2, 300 sec: 29060.8). Total num frames: 23900160. Throughput: 0: 7250.1. Samples: 4957252. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:04,217][12851] Avg episode reward: [(0, '4.350')]
+[2025-04-03 14:09:04,821][20447] Updated weights for policy 0, policy_version 5840 (0.0012)
+[2025-04-03 14:09:06,253][20447] Updated weights for policy 0, policy_version 5850 (0.0010)
+[2025-04-03 14:09:07,647][20447] Updated weights for policy 0, policy_version 5860 (0.0013)
+[2025-04-03 14:09:09,052][20447] Updated weights for policy 0, policy_version 5870 (0.0011)
+[2025-04-03 14:09:09,215][12851] Fps is (10 sec: 29490.9, 60 sec: 29081.6, 300 sec: 29060.8). Total num frames: 24047616. Throughput: 0: 7245.7. Samples: 5000912. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:09,216][12851] Avg episode reward: [(0, '4.321')]
+[2025-04-03 14:09:10,482][20447] Updated weights for policy 0, policy_version 5880 (0.0010)
+[2025-04-03 14:09:11,860][20447] Updated weights for policy 0, policy_version 5890 (0.0011)
+[2025-04-03 14:09:13,250][20447] Updated weights for policy 0, policy_version 5900 (0.0009)
+[2025-04-03 14:09:14,215][12851] Fps is (10 sec: 29082.0, 60 sec: 29013.3, 300 sec: 29060.8). Total num frames: 24190976. Throughput: 0: 7262.3. Samples: 5044680. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:14,217][12851] Avg episode reward: [(0, '4.270')]
+[2025-04-03 14:09:14,663][20447] Updated weights for policy 0, policy_version 5910 (0.0010)
+[2025-04-03 14:09:16,071][20447] Updated weights for policy 0, policy_version 5920 (0.0010)
+[2025-04-03 14:09:17,472][20447] Updated weights for policy 0, policy_version 5930 (0.0012)
+[2025-04-03 14:09:18,851][20447] Updated weights for policy 0, policy_version 5940 (0.0009)
+[2025-04-03 14:09:19,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29013.3, 300 sec: 29060.8). Total num frames: 24338432. Throughput: 0: 7269.5. Samples: 5066724. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:09:19,217][12851] Avg episode reward: [(0, '4.419')]
+[2025-04-03 14:09:20,231][20447] Updated weights for policy 0, policy_version 5950 (0.0012)
+[2025-04-03 14:09:21,651][20447] Updated weights for policy 0, policy_version 5960 (0.0009)
+[2025-04-03 14:09:23,037][20447] Updated weights for policy 0, policy_version 5970 (0.0011)
+[2025-04-03 14:09:24,215][12851] Fps is (10 sec: 29491.4, 60 sec: 29081.6, 300 sec: 29074.7). Total num frames: 24485888. Throughput: 0: 7281.8. Samples: 5110698. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:09:24,217][12851] Avg episode reward: [(0, '4.570')]
+[2025-04-03 14:09:24,458][20447] Updated weights for policy 0, policy_version 5980 (0.0010)
+[2025-04-03 14:09:25,914][20447] Updated weights for policy 0, policy_version 5990 (0.0011)
+[2025-04-03 14:09:27,313][20447] Updated weights for policy 0, policy_version 6000 (0.0010)
+[2025-04-03 14:09:28,718][20447] Updated weights for policy 0, policy_version 6010 (0.0010)
+[2025-04-03 14:09:29,215][12851] Fps is (10 sec: 29081.2, 60 sec: 29081.6, 300 sec: 29060.8). Total num frames: 24629248. Throughput: 0: 7280.6. Samples: 5153946. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:09:29,217][12851] Avg episode reward: [(0, '4.569')]
+[2025-04-03 14:09:29,224][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000006013_24629248.pth...
+[2025-04-03 14:09:29,346][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000004311_17657856.pth
+[2025-04-03 14:09:30,120][20447] Updated weights for policy 0, policy_version 6020 (0.0011)
+[2025-04-03 14:09:31,529][20447] Updated weights for policy 0, policy_version 6030 (0.0010)
+[2025-04-03 14:09:32,941][20447] Updated weights for policy 0, policy_version 6040 (0.0011)
+[2025-04-03 14:09:34,215][12851] Fps is (10 sec: 28671.8, 60 sec: 29081.6, 300 sec: 29046.9). Total num frames: 24772608. Throughput: 0: 7279.4. Samples: 5175756. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:34,216][12851] Avg episode reward: [(0, '4.521')]
+[2025-04-03 14:09:34,388][20447] Updated weights for policy 0, policy_version 6050 (0.0012)
+[2025-04-03 14:09:35,823][20447] Updated weights for policy 0, policy_version 6060 (0.0009)
+[2025-04-03 14:09:37,239][20447] Updated weights for policy 0, policy_version 6070 (0.0010)
+[2025-04-03 14:09:38,647][20447] Updated weights for policy 0, policy_version 6080 (0.0011)
+[2025-04-03 14:09:39,215][12851] Fps is (10 sec: 28672.4, 60 sec: 29013.3, 300 sec: 29046.9). Total num frames: 24915968. Throughput: 0: 7271.3. Samples: 5218772. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:39,216][12851] Avg episode reward: [(0, '4.347')]
+[2025-04-03 14:09:40,109][20447] Updated weights for policy 0, policy_version 6090 (0.0011)
+[2025-04-03 14:09:41,524][20447] Updated weights for policy 0, policy_version 6100 (0.0009)
+[2025-04-03 14:09:42,962][20447] Updated weights for policy 0, policy_version 6110 (0.0011)
+[2025-04-03 14:09:44,215][12851] Fps is (10 sec: 28672.4, 60 sec: 29013.4, 300 sec: 29033.0). Total num frames: 25059328. Throughput: 0: 7258.0. Samples: 5261868. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:44,216][12851] Avg episode reward: [(0, '4.590')]
+[2025-04-03 14:09:44,400][20447] Updated weights for policy 0, policy_version 6120 (0.0012)
+[2025-04-03 14:09:45,831][20447] Updated weights for policy 0, policy_version 6130 (0.0012)
+[2025-04-03 14:09:47,242][20447] Updated weights for policy 0, policy_version 6140 (0.0010)
+[2025-04-03 14:09:48,640][20447] Updated weights for policy 0, policy_version 6150 (0.0011)
+[2025-04-03 14:09:49,215][12851] Fps is (10 sec: 28672.1, 60 sec: 29013.4, 300 sec: 29033.0). Total num frames: 25202688. Throughput: 0: 7245.3. Samples: 5283290. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:49,217][12851] Avg episode reward: [(0, '4.883')]
+[2025-04-03 14:09:49,222][20429] Saving new best policy, reward=4.883!
+[2025-04-03 14:09:50,121][20447] Updated weights for policy 0, policy_version 6160 (0.0010)
+[2025-04-03 14:09:51,558][20447] Updated weights for policy 0, policy_version 6170 (0.0009)
+[2025-04-03 14:09:52,993][20447] Updated weights for policy 0, policy_version 6180 (0.0012)
+[2025-04-03 14:09:54,215][12851] Fps is (10 sec: 28671.8, 60 sec: 28945.0, 300 sec: 29019.1). Total num frames: 25346048. Throughput: 0: 7227.9. Samples: 5326168. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:09:54,217][12851] Avg episode reward: [(0, '4.420')]
+[2025-04-03 14:09:54,405][20447] Updated weights for policy 0, policy_version 6190 (0.0011)
+[2025-04-03 14:09:55,803][20447] Updated weights for policy 0, policy_version 6200 (0.0009)
+[2025-04-03 14:09:57,188][20447] Updated weights for policy 0, policy_version 6210 (0.0009)
+[2025-04-03 14:09:58,617][20447] Updated weights for policy 0, policy_version 6220 (0.0011)
+[2025-04-03 14:09:59,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29013.3, 300 sec: 29019.1). Total num frames: 25493504. Throughput: 0: 7223.6. Samples: 5369740. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:09:59,216][12851] Avg episode reward: [(0, '4.572')]
+[2025-04-03 14:10:00,047][20447] Updated weights for policy 0, policy_version 6230 (0.0012)
+[2025-04-03 14:10:01,562][20447] Updated weights for policy 0, policy_version 6240 (0.0011)
+[2025-04-03 14:10:02,990][20447] Updated weights for policy 0, policy_version 6250 (0.0009)
+[2025-04-03 14:10:04,215][12851] Fps is (10 sec: 29081.8, 60 sec: 28945.2, 300 sec: 29019.1). Total num frames: 25636864. Throughput: 0: 7198.4. Samples: 5390650. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:10:04,216][12851] Avg episode reward: [(0, '4.127')]
+[2025-04-03 14:10:04,381][20447] Updated weights for policy 0, policy_version 6260 (0.0010)
+[2025-04-03 14:10:05,783][20447] Updated weights for policy 0, policy_version 6270 (0.0009)
+[2025-04-03 14:10:07,205][20447] Updated weights for policy 0, policy_version 6280 (0.0011)
+[2025-04-03 14:10:08,579][20447] Updated weights for policy 0, policy_version 6290 (0.0010)
+[2025-04-03 14:10:09,215][12851] Fps is (10 sec: 28671.7, 60 sec: 28876.8, 300 sec: 29005.2). Total num frames: 25780224. Throughput: 0: 7191.8. Samples: 5434330. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:09,217][12851] Avg episode reward: [(0, '4.342')]
+[2025-04-03 14:10:10,017][20447] Updated weights for policy 0, policy_version 6300 (0.0012)
+[2025-04-03 14:10:11,456][20447] Updated weights for policy 0, policy_version 6310 (0.0011)
+[2025-04-03 14:10:12,856][20447] Updated weights for policy 0, policy_version 6320 (0.0010)
+[2025-04-03 14:10:14,215][12851] Fps is (10 sec: 28671.7, 60 sec: 28876.8, 300 sec: 28991.3). Total num frames: 25923584. Throughput: 0: 7193.0. Samples: 5477630. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:10:14,217][12851] Avg episode reward: [(0, '4.581')]
+[2025-04-03 14:10:14,295][20447] Updated weights for policy 0, policy_version 6330 (0.0010)
+[2025-04-03 14:10:15,698][20447] Updated weights for policy 0, policy_version 6340 (0.0010)
+[2025-04-03 14:10:17,093][20447] Updated weights for policy 0, policy_version 6350 (0.0011)
+[2025-04-03 14:10:18,533][20447] Updated weights for policy 0, policy_version 6360 (0.0010)
+[2025-04-03 14:10:19,215][12851] Fps is (10 sec: 28672.4, 60 sec: 28808.5, 300 sec: 28991.4). Total num frames: 26066944. Throughput: 0: 7191.2. Samples: 5499360. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:10:19,217][12851] Avg episode reward: [(0, '4.412')]
+[2025-04-03 14:10:20,102][20447] Updated weights for policy 0, policy_version 6370 (0.0012)
+[2025-04-03 14:10:21,647][20447] Updated weights for policy 0, policy_version 6380 (0.0012)
+[2025-04-03 14:10:23,158][20447] Updated weights for policy 0, policy_version 6390 (0.0011)
+[2025-04-03 14:10:24,215][12851] Fps is (10 sec: 27853.0, 60 sec: 28603.7, 300 sec: 28963.6). Total num frames: 26202112. Throughput: 0: 7136.9. Samples: 5539934. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:24,216][12851] Avg episode reward: [(0, '4.412')]
+[2025-04-03 14:10:24,686][20447] Updated weights for policy 0, policy_version 6400 (0.0010)
+[2025-04-03 14:10:26,191][20447] Updated weights for policy 0, policy_version 6410 (0.0012)
+[2025-04-03 14:10:27,675][20447] Updated weights for policy 0, policy_version 6420 (0.0011)
+[2025-04-03 14:10:29,215][12851] Fps is (10 sec: 26623.8, 60 sec: 28399.0, 300 sec: 28908.5). Total num frames: 26333184. Throughput: 0: 7078.2. Samples: 5580386. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:10:29,216][12851] Avg episode reward: [(0, '4.243')]
+[2025-04-03 14:10:29,278][20447] Updated weights for policy 0, policy_version 6430 (0.0010)
+[2025-04-03 14:10:30,838][20447] Updated weights for policy 0, policy_version 6440 (0.0009)
+[2025-04-03 14:10:32,406][20447] Updated weights for policy 0, policy_version 6450 (0.0012)
+[2025-04-03 14:10:33,931][20447] Updated weights for policy 0, policy_version 6460 (0.0012)
+[2025-04-03 14:10:34,215][12851] Fps is (10 sec: 26623.9, 60 sec: 28262.4, 300 sec: 28880.3). Total num frames: 26468352. Throughput: 0: 7038.2. Samples: 5600008. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:34,217][12851] Avg episode reward: [(0, '4.489')]
+[2025-04-03 14:10:35,354][20447] Updated weights for policy 0, policy_version 6470 (0.0010)
+[2025-04-03 14:10:36,734][20447] Updated weights for policy 0, policy_version 6480 (0.0009)
+[2025-04-03 14:10:38,153][20447] Updated weights for policy 0, policy_version 6490 (0.0011)
+[2025-04-03 14:10:39,215][12851] Fps is (10 sec: 27852.6, 60 sec: 28262.3, 300 sec: 28866.4). Total num frames: 26611712. Throughput: 0: 7026.7. Samples: 5642370. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:10:39,218][12851] Avg episode reward: [(0, '4.518')]
+[2025-04-03 14:10:39,579][20447] Updated weights for policy 0, policy_version 6500 (0.0011)
+[2025-04-03 14:10:40,962][20447] Updated weights for policy 0, policy_version 6510 (0.0009)
+[2025-04-03 14:10:42,378][20447] Updated weights for policy 0, policy_version 6520 (0.0010)
+[2025-04-03 14:10:43,770][20447] Updated weights for policy 0, policy_version 6530 (0.0011)
+[2025-04-03 14:10:44,215][12851] Fps is (10 sec: 28672.1, 60 sec: 28262.4, 300 sec: 28852.5). Total num frames: 26755072. Throughput: 0: 7027.1. Samples: 5685958. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:44,216][12851] Avg episode reward: [(0, '4.316')]
+[2025-04-03 14:10:45,200][20447] Updated weights for policy 0, policy_version 6540 (0.0012)
+[2025-04-03 14:10:46,575][20447] Updated weights for policy 0, policy_version 6550 (0.0010)
+[2025-04-03 14:10:47,997][20447] Updated weights for policy 0, policy_version 6560 (0.0009)
+[2025-04-03 14:10:49,215][12851] Fps is (10 sec: 29081.7, 60 sec: 28330.6, 300 sec: 28880.3). Total num frames: 26902528. Throughput: 0: 7048.6. Samples: 5707836. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:49,217][12851] Avg episode reward: [(0, '4.759')]
+[2025-04-03 14:10:49,402][20447] Updated weights for policy 0, policy_version 6570 (0.0011)
+[2025-04-03 14:10:50,836][20447] Updated weights for policy 0, policy_version 6580 (0.0009)
+[2025-04-03 14:10:52,217][20447] Updated weights for policy 0, policy_version 6590 (0.0011)
+[2025-04-03 14:10:53,691][20447] Updated weights for policy 0, policy_version 6600 (0.0012)
+[2025-04-03 14:10:54,215][12851] Fps is (10 sec: 29081.3, 60 sec: 28330.6, 300 sec: 28880.3). Total num frames: 27045888. Throughput: 0: 7042.6. Samples: 5751248. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:10:54,217][12851] Avg episode reward: [(0, '4.368')]
+[2025-04-03 14:10:55,167][20447] Updated weights for policy 0, policy_version 6610 (0.0010)
+[2025-04-03 14:10:56,631][20447] Updated weights for policy 0, policy_version 6620 (0.0010)
+[2025-04-03 14:10:58,073][20447] Updated weights for policy 0, policy_version 6630 (0.0012)
+[2025-04-03 14:10:59,215][12851] Fps is (10 sec: 28672.3, 60 sec: 28262.4, 300 sec: 28894.2). Total num frames: 27189248. Throughput: 0: 7025.7. Samples: 5793788. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:10:59,216][12851] Avg episode reward: [(0, '4.553')]
+[2025-04-03 14:10:59,450][20447] Updated weights for policy 0, policy_version 6640 (0.0011)
+[2025-04-03 14:11:00,883][20447] Updated weights for policy 0, policy_version 6650 (0.0012)
+[2025-04-03 14:11:02,285][20447] Updated weights for policy 0, policy_version 6660 (0.0010)
+[2025-04-03 14:11:03,681][20447] Updated weights for policy 0, policy_version 6670 (0.0011)
+[2025-04-03 14:11:04,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28262.4, 300 sec: 28880.3). Total num frames: 27332608. Throughput: 0: 7025.1. Samples: 5815488. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:11:04,216][12851] Avg episode reward: [(0, '4.343')]
+[2025-04-03 14:11:05,095][20447] Updated weights for policy 0, policy_version 6680 (0.0008)
+[2025-04-03 14:11:06,514][20447] Updated weights for policy 0, policy_version 6690 (0.0011)
+[2025-04-03 14:11:07,906][20447] Updated weights for policy 0, policy_version 6700 (0.0009)
+[2025-04-03 14:11:09,215][12851] Fps is (10 sec: 29081.6, 60 sec: 28330.7, 300 sec: 28880.3). Total num frames: 27480064. Throughput: 0: 7092.5. Samples: 5859096. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:11:09,217][12851] Avg episode reward: [(0, '4.423')]
+[2025-04-03 14:11:09,342][20447] Updated weights for policy 0, policy_version 6710 (0.0011)
+[2025-04-03 14:11:10,721][20447] Updated weights for policy 0, policy_version 6720 (0.0011)
+[2025-04-03 14:11:12,096][20447] Updated weights for policy 0, policy_version 6730 (0.0010)
+[2025-04-03 14:11:13,491][20447] Updated weights for policy 0, policy_version 6740 (0.0012)
+[2025-04-03 14:11:14,215][12851] Fps is (10 sec: 29491.3, 60 sec: 28399.0, 300 sec: 28894.2). Total num frames: 27627520. Throughput: 0: 7173.6. Samples: 5903198. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:11:14,216][12851] Avg episode reward: [(0, '4.316')]
+[2025-04-03 14:11:14,860][20447] Updated weights for policy 0, policy_version 6750 (0.0010)
+[2025-04-03 14:11:16,270][20447] Updated weights for policy 0, policy_version 6760 (0.0011)
+[2025-04-03 14:11:17,653][20447] Updated weights for policy 0, policy_version 6770 (0.0011)
+[2025-04-03 14:11:19,071][20447] Updated weights for policy 0, policy_version 6780 (0.0011)
+[2025-04-03 14:11:19,215][12851] Fps is (10 sec: 29491.3, 60 sec: 28467.2, 300 sec: 28894.2). Total num frames: 27774976. Throughput: 0: 7229.1. Samples: 5925316. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:11:19,216][12851] Avg episode reward: [(0, '4.392')]
+[2025-04-03 14:11:20,490][20447] Updated weights for policy 0, policy_version 6790 (0.0011)
+[2025-04-03 14:11:21,870][20447] Updated weights for policy 0, policy_version 6800 (0.0009)
+[2025-04-03 14:11:23,298][20447] Updated weights for policy 0, policy_version 6810 (0.0011)
+[2025-04-03 14:11:24,215][12851] Fps is (10 sec: 29081.3, 60 sec: 28603.7, 300 sec: 28880.3). Total num frames: 27918336. Throughput: 0: 7257.7. Samples: 5968968. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:11:24,217][12851] Avg episode reward: [(0, '4.395')]
+[2025-04-03 14:11:24,722][20447] Updated weights for policy 0, policy_version 6820 (0.0009)
+[2025-04-03 14:11:26,095][20447] Updated weights for policy 0, policy_version 6830 (0.0011)
+[2025-04-03 14:11:27,502][20447] Updated weights for policy 0, policy_version 6840 (0.0011)
+[2025-04-03 14:11:28,921][20447] Updated weights for policy 0, policy_version 6850 (0.0011)
+[2025-04-03 14:11:29,215][12851] Fps is (10 sec: 29081.2, 60 sec: 28876.8, 300 sec: 28894.1). Total num frames: 28065792. Throughput: 0: 7263.3. Samples: 6012808. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:11:29,216][12851] Avg episode reward: [(0, '4.391')]
+[2025-04-03 14:11:29,224][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000006852_28065792.pth...
+[2025-04-03 14:11:29,331][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000005162_21143552.pth
+[2025-04-03 14:11:30,320][20447] Updated weights for policy 0, policy_version 6860 (0.0011)
+[2025-04-03 14:11:31,699][20447] Updated weights for policy 0, policy_version 6870 (0.0010)
+[2025-04-03 14:11:33,093][20447] Updated weights for policy 0, policy_version 6880 (0.0010)
+[2025-04-03 14:11:34,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29013.3, 300 sec: 28880.3). Total num frames: 28209152. Throughput: 0: 7263.1. Samples: 6034676. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:11:34,217][12851] Avg episode reward: [(0, '4.562')]
+[2025-04-03 14:11:34,518][20447] Updated weights for policy 0, policy_version 6890 (0.0009)
+[2025-04-03 14:11:35,894][20447] Updated weights for policy 0, policy_version 6900 (0.0011)
+[2025-04-03 14:11:37,301][20447] Updated weights for policy 0, policy_version 6910 (0.0012)
+[2025-04-03 14:11:38,746][20447] Updated weights for policy 0, policy_version 6920 (0.0009)
+[2025-04-03 14:11:39,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29081.6, 300 sec: 28880.3). Total num frames: 28356608. Throughput: 0: 7271.7. Samples: 6078474. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:11:39,217][12851] Avg episode reward: [(0, '4.569')]
+[2025-04-03 14:11:40,115][20447] Updated weights for policy 0, policy_version 6930 (0.0009)
+[2025-04-03 14:11:41,494][20447] Updated weights for policy 0, policy_version 6940 (0.0011)
+[2025-04-03 14:11:42,927][20447] Updated weights for policy 0, policy_version 6950 (0.0012)
+[2025-04-03 14:11:44,215][12851] Fps is (10 sec: 29491.1, 60 sec: 29149.8, 300 sec: 28880.3). Total num frames: 28504064. Throughput: 0: 7301.5. Samples: 6122354. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:11:44,216][12851] Avg episode reward: [(0, '4.541')]
+[2025-04-03 14:11:44,324][20447] Updated weights for policy 0, policy_version 6960 (0.0011)
+[2025-04-03 14:11:45,743][20447] Updated weights for policy 0, policy_version 6970 (0.0011)
+[2025-04-03 14:11:47,142][20447] Updated weights for policy 0, policy_version 6980 (0.0008)
+[2025-04-03 14:11:48,537][20447] Updated weights for policy 0, policy_version 6990 (0.0011)
+[2025-04-03 14:11:49,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29081.6, 300 sec: 28880.3). Total num frames: 28647424. Throughput: 0: 7304.6. Samples: 6144196. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:11:49,216][12851] Avg episode reward: [(0, '4.467')]
+[2025-04-03 14:11:49,916][20447] Updated weights for policy 0, policy_version 7000 (0.0009)
+[2025-04-03 14:11:51,315][20447] Updated weights for policy 0, policy_version 7010 (0.0010)
+[2025-04-03 14:11:52,744][20447] Updated weights for policy 0, policy_version 7020 (0.0010)
+[2025-04-03 14:11:54,109][20447] Updated weights for policy 0, policy_version 7030 (0.0012)
+[2025-04-03 14:11:54,215][12851] Fps is (10 sec: 29082.0, 60 sec: 29149.9, 300 sec: 28894.2). Total num frames: 28794880. Throughput: 0: 7310.6. Samples: 6188074. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:11:54,216][12851] Avg episode reward: [(0, '4.281')]
+[2025-04-03 14:11:55,504][20447] Updated weights for policy 0, policy_version 7040 (0.0012)
+[2025-04-03 14:11:56,949][20447] Updated weights for policy 0, policy_version 7050 (0.0009)
+[2025-04-03 14:11:58,340][20447] Updated weights for policy 0, policy_version 7060 (0.0009)
+[2025-04-03 14:11:59,215][12851] Fps is (10 sec: 29490.8, 60 sec: 29218.1, 300 sec: 28894.1). Total num frames: 28942336. Throughput: 0: 7305.0. Samples: 6231922. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:11:59,216][12851] Avg episode reward: [(0, '4.400')]
+[2025-04-03 14:11:59,742][20447] Updated weights for policy 0, policy_version 7070 (0.0010)
+[2025-04-03 14:12:01,166][20447] Updated weights for policy 0, policy_version 7080 (0.0010)
+[2025-04-03 14:12:02,566][20447] Updated weights for policy 0, policy_version 7090 (0.0009)
+[2025-04-03 14:12:03,974][20447] Updated weights for policy 0, policy_version 7100 (0.0011)
+[2025-04-03 14:12:04,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29218.2, 300 sec: 28894.2). Total num frames: 29085696. Throughput: 0: 7297.0. Samples: 6253680. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:04,216][12851] Avg episode reward: [(0, '4.424')]
+[2025-04-03 14:12:05,436][20447] Updated weights for policy 0, policy_version 7110 (0.0011)
+[2025-04-03 14:12:06,854][20447] Updated weights for policy 0, policy_version 7120 (0.0009)
+[2025-04-03 14:12:08,261][20447] Updated weights for policy 0, policy_version 7130 (0.0009)
+[2025-04-03 14:12:09,215][12851] Fps is (10 sec: 28672.3, 60 sec: 29149.9, 300 sec: 28894.1). Total num frames: 29229056. Throughput: 0: 7288.2. Samples: 6296938. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:09,216][12851] Avg episode reward: [(0, '4.510')]
+[2025-04-03 14:12:09,670][20447] Updated weights for policy 0, policy_version 7140 (0.0011)
+[2025-04-03 14:12:11,078][20447] Updated weights for policy 0, policy_version 7150 (0.0010)
+[2025-04-03 14:12:12,482][20447] Updated weights for policy 0, policy_version 7160 (0.0011)
+[2025-04-03 14:12:13,893][20447] Updated weights for policy 0, policy_version 7170 (0.0009)
+[2025-04-03 14:12:14,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29149.9, 300 sec: 28908.0). Total num frames: 29376512. Throughput: 0: 7285.6. Samples: 6340658. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:14,216][12851] Avg episode reward: [(0, '4.434')]
+[2025-04-03 14:12:15,310][20447] Updated weights for policy 0, policy_version 7180 (0.0012)
+[2025-04-03 14:12:16,704][20447] Updated weights for policy 0, policy_version 7190 (0.0009)
+[2025-04-03 14:12:18,094][20447] Updated weights for policy 0, policy_version 7200 (0.0011)
+[2025-04-03 14:12:19,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29081.6, 300 sec: 28894.2). Total num frames: 29519872. Throughput: 0: 7281.8. Samples: 6362358. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:12:19,216][12851] Avg episode reward: [(0, '4.380')]
+[2025-04-03 14:12:19,561][20447] Updated weights for policy 0, policy_version 7210 (0.0013)
+[2025-04-03 14:12:20,969][20447] Updated weights for policy 0, policy_version 7220 (0.0012)
+[2025-04-03 14:12:22,420][20447] Updated weights for policy 0, policy_version 7230 (0.0011)
+[2025-04-03 14:12:23,822][20447] Updated weights for policy 0, policy_version 7240 (0.0008)
+[2025-04-03 14:12:24,215][12851] Fps is (10 sec: 28671.8, 60 sec: 29081.6, 300 sec: 28894.2). Total num frames: 29663232. Throughput: 0: 7271.7. Samples: 6405702. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:12:24,216][12851] Avg episode reward: [(0, '4.450')]
+[2025-04-03 14:12:25,184][20447] Updated weights for policy 0, policy_version 7250 (0.0011)
+[2025-04-03 14:12:26,591][20447] Updated weights for policy 0, policy_version 7260 (0.0012)
+[2025-04-03 14:12:28,013][20447] Updated weights for policy 0, policy_version 7270 (0.0010)
+[2025-04-03 14:12:29,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29081.7, 300 sec: 28908.1). Total num frames: 29810688. Throughput: 0: 7263.3. Samples: 6449200. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:29,217][12851] Avg episode reward: [(0, '4.265')]
+[2025-04-03 14:12:29,463][20447] Updated weights for policy 0, policy_version 7280 (0.0010)
+[2025-04-03 14:12:30,906][20447] Updated weights for policy 0, policy_version 7290 (0.0011)
+[2025-04-03 14:12:32,412][20447] Updated weights for policy 0, policy_version 7300 (0.0009)
+[2025-04-03 14:12:33,925][20447] Updated weights for policy 0, policy_version 7310 (0.0009)
+[2025-04-03 14:12:34,216][12851] Fps is (10 sec: 28671.8, 60 sec: 29013.3, 300 sec: 28880.3). Total num frames: 29949952. Throughput: 0: 7246.3. Samples: 6470278. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:34,217][12851] Avg episode reward: [(0, '4.437')]
+[2025-04-03 14:12:35,457][20447] Updated weights for policy 0, policy_version 7320 (0.0012)
+[2025-04-03 14:12:37,009][20447] Updated weights for policy 0, policy_version 7330 (0.0014)
+[2025-04-03 14:12:38,532][20447] Updated weights for policy 0, policy_version 7340 (0.0011)
+[2025-04-03 14:12:39,215][12851] Fps is (10 sec: 27033.4, 60 sec: 28740.3, 300 sec: 28824.7). Total num frames: 30081024. Throughput: 0: 7156.9. Samples: 6510136. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:12:39,217][12851] Avg episode reward: [(0, '4.353')]
+[2025-04-03 14:12:40,090][20447] Updated weights for policy 0, policy_version 7350 (0.0012)
+[2025-04-03 14:12:41,588][20447] Updated weights for policy 0, policy_version 7360 (0.0010)
+[2025-04-03 14:12:42,991][20447] Updated weights for policy 0, policy_version 7370 (0.0012)
+[2025-04-03 14:12:44,215][12851] Fps is (10 sec: 27443.0, 60 sec: 28672.0, 300 sec: 28824.7). Total num frames: 30224384. Throughput: 0: 7118.2. Samples: 6552242. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:12:44,217][12851] Avg episode reward: [(0, '4.354')]
+[2025-04-03 14:12:44,376][20447] Updated weights for policy 0, policy_version 7380 (0.0009)
+[2025-04-03 14:12:45,729][20447] Updated weights for policy 0, policy_version 7390 (0.0009)
+[2025-04-03 14:12:47,131][20447] Updated weights for policy 0, policy_version 7400 (0.0010)
+[2025-04-03 14:12:48,567][20447] Updated weights for policy 0, policy_version 7410 (0.0010)
+[2025-04-03 14:12:49,215][12851] Fps is (10 sec: 28672.2, 60 sec: 28672.0, 300 sec: 28810.8). Total num frames: 30367744. Throughput: 0: 7122.7. Samples: 6574204. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:12:49,217][12851] Avg episode reward: [(0, '4.530')]
+[2025-04-03 14:12:49,966][20447] Updated weights for policy 0, policy_version 7420 (0.0010)
+[2025-04-03 14:12:51,391][20447] Updated weights for policy 0, policy_version 7430 (0.0010)
+[2025-04-03 14:12:52,779][20447] Updated weights for policy 0, policy_version 7440 (0.0010)
+[2025-04-03 14:12:54,150][20447] Updated weights for policy 0, policy_version 7450 (0.0009)
+[2025-04-03 14:12:54,215][12851] Fps is (10 sec: 29082.1, 60 sec: 28672.0, 300 sec: 28824.8). Total num frames: 30515200. Throughput: 0: 7135.2. Samples: 6618022. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:12:54,216][12851] Avg episode reward: [(0, '4.458')]
+[2025-04-03 14:12:55,532][20447] Updated weights for policy 0, policy_version 7460 (0.0010)
+[2025-04-03 14:12:56,977][20447] Updated weights for policy 0, policy_version 7470 (0.0009)
+[2025-04-03 14:12:58,379][20447] Updated weights for policy 0, policy_version 7480 (0.0011)
+[2025-04-03 14:12:59,215][12851] Fps is (10 sec: 29491.3, 60 sec: 28672.1, 300 sec: 28824.7). Total num frames: 30662656. Throughput: 0: 7139.7. Samples: 6661944. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:12:59,216][12851] Avg episode reward: [(0, '4.637')]
+[2025-04-03 14:12:59,782][20447] Updated weights for policy 0, policy_version 7490 (0.0009)
+[2025-04-03 14:13:01,152][20447] Updated weights for policy 0, policy_version 7500 (0.0011)
+[2025-04-03 14:13:02,563][20447] Updated weights for policy 0, policy_version 7510 (0.0011)
+[2025-04-03 14:13:03,973][20447] Updated weights for policy 0, policy_version 7520 (0.0009)
+[2025-04-03 14:13:04,215][12851] Fps is (10 sec: 29081.5, 60 sec: 28672.0, 300 sec: 28824.7). Total num frames: 30806016. Throughput: 0: 7144.3. Samples: 6683850. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:13:04,217][12851] Avg episode reward: [(0, '4.366')]
+[2025-04-03 14:13:05,385][20447] Updated weights for policy 0, policy_version 7530 (0.0010)
+[2025-04-03 14:13:06,806][20447] Updated weights for policy 0, policy_version 7540 (0.0009)
+[2025-04-03 14:13:08,213][20447] Updated weights for policy 0, policy_version 7550 (0.0010)
+[2025-04-03 14:13:09,215][12851] Fps is (10 sec: 29081.6, 60 sec: 28740.3, 300 sec: 28824.7). Total num frames: 30953472. Throughput: 0: 7149.3. Samples: 6727420. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:13:09,216][12851] Avg episode reward: [(0, '4.330')]
+[2025-04-03 14:13:09,614][20447] Updated weights for policy 0, policy_version 7560 (0.0009)
+[2025-04-03 14:13:11,025][20447] Updated weights for policy 0, policy_version 7570 (0.0012)
+[2025-04-03 14:13:12,406][20447] Updated weights for policy 0, policy_version 7580 (0.0011)
+[2025-04-03 14:13:13,774][20447] Updated weights for policy 0, policy_version 7590 (0.0008)
+[2025-04-03 14:13:14,215][12851] Fps is (10 sec: 29491.4, 60 sec: 28740.3, 300 sec: 28824.7). Total num frames: 31100928. Throughput: 0: 7158.7. Samples: 6771342. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:13:14,216][12851] Avg episode reward: [(0, '4.259')]
+[2025-04-03 14:13:15,202][20447] Updated weights for policy 0, policy_version 7600 (0.0011)
+[2025-04-03 14:13:16,625][20447] Updated weights for policy 0, policy_version 7610 (0.0010)
+[2025-04-03 14:13:18,025][20447] Updated weights for policy 0, policy_version 7620 (0.0009)
+[2025-04-03 14:13:19,215][12851] Fps is (10 sec: 29081.6, 60 sec: 28740.3, 300 sec: 28824.7). Total num frames: 31244288. Throughput: 0: 7175.5. Samples: 6793174. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:13:19,216][12851] Avg episode reward: [(0, '4.520')]
+[2025-04-03 14:13:19,409][20447] Updated weights for policy 0, policy_version 7630 (0.0009)
+[2025-04-03 14:13:20,798][20447] Updated weights for policy 0, policy_version 7640 (0.0010)
+[2025-04-03 14:13:22,172][20447] Updated weights for policy 0, policy_version 7650 (0.0009)
+[2025-04-03 14:13:23,566][20447] Updated weights for policy 0, policy_version 7660 (0.0010)
+[2025-04-03 14:13:24,215][12851] Fps is (10 sec: 29081.5, 60 sec: 28808.5, 300 sec: 28838.6). Total num frames: 31391744. Throughput: 0: 7268.9. Samples: 6837238. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:13:24,216][12851] Avg episode reward: [(0, '4.538')]
+[2025-04-03 14:13:24,979][20447] Updated weights for policy 0, policy_version 7670 (0.0008)
+[2025-04-03 14:13:26,423][20447] Updated weights for policy 0, policy_version 7680 (0.0012)
+[2025-04-03 14:13:27,804][20447] Updated weights for policy 0, policy_version 7690 (0.0009)
+[2025-04-03 14:13:29,174][20447] Updated weights for policy 0, policy_version 7700 (0.0010)
+[2025-04-03 14:13:29,215][12851] Fps is (10 sec: 29491.1, 60 sec: 28808.5, 300 sec: 28852.5). Total num frames: 31539200. Throughput: 0: 7308.6. Samples: 6881126. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:13:29,216][12851] Avg episode reward: [(0, '4.497')]
+[2025-04-03 14:13:29,223][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000007700_31539200.pth...
+[2025-04-03 14:13:29,300][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000006013_24629248.pth
+[2025-04-03 14:13:30,594][20447] Updated weights for policy 0, policy_version 7710 (0.0011)
+[2025-04-03 14:13:32,000][20447] Updated weights for policy 0, policy_version 7720 (0.0010)
+[2025-04-03 14:13:33,416][20447] Updated weights for policy 0, policy_version 7730 (0.0011)
+[2025-04-03 14:13:34,215][12851] Fps is (10 sec: 29081.5, 60 sec: 28876.8, 300 sec: 28838.6). Total num frames: 31682560. Throughput: 0: 7301.8. Samples: 6902786. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:13:34,217][12851] Avg episode reward: [(0, '4.427')]
+[2025-04-03 14:13:34,850][20447] Updated weights for policy 0, policy_version 7740 (0.0010)
+[2025-04-03 14:13:36,230][20447] Updated weights for policy 0, policy_version 7750 (0.0011)
+[2025-04-03 14:13:37,597][20447] Updated weights for policy 0, policy_version 7760 (0.0009)
+[2025-04-03 14:13:38,979][20447] Updated weights for policy 0, policy_version 7770 (0.0009)
+[2025-04-03 14:13:39,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29149.9, 300 sec: 28852.5). Total num frames: 31830016. Throughput: 0: 7312.3. Samples: 6947074. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:13:39,216][12851] Avg episode reward: [(0, '4.568')]
+[2025-04-03 14:13:40,411][20447] Updated weights for policy 0, policy_version 7780 (0.0009)
+[2025-04-03 14:13:41,836][20447] Updated weights for policy 0, policy_version 7790 (0.0009)
+[2025-04-03 14:13:43,240][20447] Updated weights for policy 0, policy_version 7800 (0.0010)
+[2025-04-03 14:13:44,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29150.0, 300 sec: 28852.5). Total num frames: 31973376. Throughput: 0: 7293.5. Samples: 6990150. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:13:44,217][12851] Avg episode reward: [(0, '4.311')]
+[2025-04-03 14:13:44,672][20447] Updated weights for policy 0, policy_version 7810 (0.0011)
+[2025-04-03 14:13:46,080][20447] Updated weights for policy 0, policy_version 7820 (0.0009)
+[2025-04-03 14:13:47,467][20447] Updated weights for policy 0, policy_version 7830 (0.0011)
+[2025-04-03 14:13:48,843][20447] Updated weights for policy 0, policy_version 7840 (0.0014)
+[2025-04-03 14:13:49,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29218.1, 300 sec: 28852.5). Total num frames: 32120832. Throughput: 0: 7299.6. Samples: 7012334. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:13:49,217][12851] Avg episode reward: [(0, '4.242')]
+[2025-04-03 14:13:50,260][20447] Updated weights for policy 0, policy_version 7850 (0.0012)
+[2025-04-03 14:13:51,655][20447] Updated weights for policy 0, policy_version 7860 (0.0011)
+[2025-04-03 14:13:53,115][20447] Updated weights for policy 0, policy_version 7870 (0.0010)
+[2025-04-03 14:13:54,215][12851] Fps is (10 sec: 29491.2, 60 sec: 29218.1, 300 sec: 28866.4). Total num frames: 32268288. Throughput: 0: 7298.1. Samples: 7055836. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:13:54,217][12851] Avg episode reward: [(0, '4.311')]
+[2025-04-03 14:13:54,517][20447] Updated weights for policy 0, policy_version 7880 (0.0009)
+[2025-04-03 14:13:55,896][20447] Updated weights for policy 0, policy_version 7890 (0.0011)
+[2025-04-03 14:13:57,297][20447] Updated weights for policy 0, policy_version 7900 (0.0008)
+[2025-04-03 14:13:58,698][20447] Updated weights for policy 0, policy_version 7910 (0.0009)
+[2025-04-03 14:13:59,215][12851] Fps is (10 sec: 29081.4, 60 sec: 29149.8, 300 sec: 28852.5). Total num frames: 32411648. Throughput: 0: 7298.0. Samples: 7099754. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:13:59,217][12851] Avg episode reward: [(0, '4.489')]
+[2025-04-03 14:14:00,063][20447] Updated weights for policy 0, policy_version 7920 (0.0009)
+[2025-04-03 14:14:01,466][20447] Updated weights for policy 0, policy_version 7930 (0.0011)
+[2025-04-03 14:14:02,891][20447] Updated weights for policy 0, policy_version 7940 (0.0011)
+[2025-04-03 14:14:04,216][12851] Fps is (10 sec: 29080.5, 60 sec: 29218.0, 300 sec: 28852.5). Total num frames: 32559104. Throughput: 0: 7303.6. Samples: 7121840. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:14:04,217][12851] Avg episode reward: [(0, '4.314')]
+[2025-04-03 14:14:04,303][20447] Updated weights for policy 0, policy_version 7950 (0.0009)
+[2025-04-03 14:14:05,701][20447] Updated weights for policy 0, policy_version 7960 (0.0011)
+[2025-04-03 14:14:07,104][20447] Updated weights for policy 0, policy_version 7970 (0.0009)
+[2025-04-03 14:14:08,554][20447] Updated weights for policy 0, policy_version 7980 (0.0010)
+[2025-04-03 14:14:09,215][12851] Fps is (10 sec: 29081.7, 60 sec: 29149.9, 300 sec: 28852.5). Total num frames: 32702464. Throughput: 0: 7291.5. Samples: 7165354. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:14:09,217][12851] Avg episode reward: [(0, '4.277')]
+[2025-04-03 14:14:10,067][20447] Updated weights for policy 0, policy_version 7990 (0.0010)
+[2025-04-03 14:14:11,653][20447] Updated weights for policy 0, policy_version 8000 (0.0011)
+[2025-04-03 14:14:13,155][20447] Updated weights for policy 0, policy_version 8010 (0.0012)
+[2025-04-03 14:14:14,215][12851] Fps is (10 sec: 27853.8, 60 sec: 28945.0, 300 sec: 28810.8). Total num frames: 32837632. Throughput: 0: 7212.1. Samples: 7205670. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:14:14,216][12851] Avg episode reward: [(0, '4.444')]
+[2025-04-03 14:14:14,677][20447] Updated weights for policy 0, policy_version 8020 (0.0010)
+[2025-04-03 14:14:16,169][20447] Updated weights for policy 0, policy_version 8030 (0.0011)
+[2025-04-03 14:14:17,661][20447] Updated weights for policy 0, policy_version 8040 (0.0012)
+[2025-04-03 14:14:19,180][20447] Updated weights for policy 0, policy_version 8050 (0.0012)
+[2025-04-03 14:14:19,215][12851] Fps is (10 sec: 27033.2, 60 sec: 28808.4, 300 sec: 28769.2). Total num frames: 32972800. Throughput: 0: 7184.3. Samples: 7226082. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:14:19,217][12851] Avg episode reward: [(0, '4.456')]
+[2025-04-03 14:14:20,631][20447] Updated weights for policy 0, policy_version 8060 (0.0010)
+[2025-04-03 14:14:22,060][20447] Updated weights for policy 0, policy_version 8070 (0.0008)
+[2025-04-03 14:14:23,442][20447] Updated weights for policy 0, policy_version 8080 (0.0010)
+[2025-04-03 14:14:24,215][12851] Fps is (10 sec: 27852.9, 60 sec: 28740.3, 300 sec: 28769.2). Total num frames: 33116160. Throughput: 0: 7141.0. Samples: 7268420. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2025-04-03 14:14:24,216][12851] Avg episode reward: [(0, '4.411')]
+[2025-04-03 14:14:24,828][20447] Updated weights for policy 0, policy_version 8090 (0.0010)
+[2025-04-03 14:14:26,193][20447] Updated weights for policy 0, policy_version 8100 (0.0010)
+[2025-04-03 14:14:27,599][20447] Updated weights for policy 0, policy_version 8110 (0.0010)
+[2025-04-03 14:14:28,980][20447] Updated weights for policy 0, policy_version 8120 (0.0011)
+[2025-04-03 14:14:29,215][12851] Fps is (10 sec: 29081.8, 60 sec: 28740.2, 300 sec: 28783.1). Total num frames: 33263616. Throughput: 0: 7166.8. Samples: 7312658. Policy #0 lag: (min: 0.0, avg: 1.0, max: 3.0)
+[2025-04-03 14:14:29,217][12851] Avg episode reward: [(0, '4.285')]
+[2025-04-03 14:14:30,407][20447] Updated weights for policy 0, policy_version 8130 (0.0010)
+[2025-04-03 14:14:31,772][20447] Updated weights for policy 0, policy_version 8140 (0.0010)
+[2025-04-03 14:14:33,174][20447] Updated weights for policy 0, policy_version 8150 (0.0010)
+[2025-04-03 14:14:34,215][12851] Fps is (10 sec: 29490.6, 60 sec: 28808.5, 300 sec: 28796.9). Total num frames: 33411072. Throughput: 0: 7167.8. Samples: 7334888. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:14:34,216][12851] Avg episode reward: [(0, '4.266')]
+[2025-04-03 14:14:34,541][20447] Updated weights for policy 0, policy_version 8160 (0.0008)
+[2025-04-03 14:14:35,924][20447] Updated weights for policy 0, policy_version 8170 (0.0009)
+[2025-04-03 14:14:37,343][20447] Updated weights for policy 0, policy_version 8180 (0.0009)
+[2025-04-03 14:14:38,736][20447] Updated weights for policy 0, policy_version 8190 (0.0012)
+[2025-04-03 14:14:39,215][12851] Fps is (10 sec: 29491.6, 60 sec: 28808.6, 300 sec: 28810.8). Total num frames: 33558528. Throughput: 0: 7177.2. Samples: 7378810. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:14:39,217][12851] Avg episode reward: [(0, '4.484')]
+[2025-04-03 14:14:40,158][20447] Updated weights for policy 0, policy_version 8200 (0.0009)
+[2025-04-03 14:14:41,555][20447] Updated weights for policy 0, policy_version 8210 (0.0009)
+[2025-04-03 14:14:42,949][20447] Updated weights for policy 0, policy_version 8220 (0.0010)
+[2025-04-03 14:14:44,216][12851] Fps is (10 sec: 29491.2, 60 sec: 28876.7, 300 sec: 28824.7). Total num frames: 33705984. Throughput: 0: 7180.9. Samples: 7422896. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:14:44,217][12851] Avg episode reward: [(0, '4.271')]
+[2025-04-03 14:14:44,301][20447] Updated weights for policy 0, policy_version 8230 (0.0011)
+[2025-04-03 14:14:45,735][20447] Updated weights for policy 0, policy_version 8240 (0.0011)
+[2025-04-03 14:14:47,121][20447] Updated weights for policy 0, policy_version 8250 (0.0009)
+[2025-04-03 14:14:48,534][20447] Updated weights for policy 0, policy_version 8260 (0.0011)
+[2025-04-03 14:14:49,215][12851] Fps is (10 sec: 29081.4, 60 sec: 28808.5, 300 sec: 28824.7). Total num frames: 33849344. Throughput: 0: 7175.5. Samples: 7444736. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:14:49,216][12851] Avg episode reward: [(0, '4.528')]
+[2025-04-03 14:14:49,939][20447] Updated weights for policy 0, policy_version 8270 (0.0010)
+[2025-04-03 14:14:51,321][20447] Updated weights for policy 0, policy_version 8280 (0.0011)
+[2025-04-03 14:14:52,698][20447] Updated weights for policy 0, policy_version 8290 (0.0011)
+[2025-04-03 14:14:54,110][20447] Updated weights for policy 0, policy_version 8300 (0.0009)
+[2025-04-03 14:14:54,215][12851] Fps is (10 sec: 29082.0, 60 sec: 28808.5, 300 sec: 28824.7). Total num frames: 33996800. Throughput: 0: 7186.4. Samples: 7488742. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:14:54,216][12851] Avg episode reward: [(0, '4.447')]
+[2025-04-03 14:14:55,556][20447] Updated weights for policy 0, policy_version 8310 (0.0011)
+[2025-04-03 14:14:56,959][20447] Updated weights for policy 0, policy_version 8320 (0.0012)
+[2025-04-03 14:14:58,360][20447] Updated weights for policy 0, policy_version 8330 (0.0009)
+[2025-04-03 14:14:59,215][12851] Fps is (10 sec: 29491.4, 60 sec: 28876.8, 300 sec: 28838.6). Total num frames: 34144256. Throughput: 0: 7262.0. Samples: 7532458. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:14:59,216][12851] Avg episode reward: [(0, '4.378')]
+[2025-04-03 14:14:59,736][20447] Updated weights for policy 0, policy_version 8340 (0.0010)
+[2025-04-03 14:15:01,138][20447] Updated weights for policy 0, policy_version 8350 (0.0011)
+[2025-04-03 14:15:02,521][20447] Updated weights for policy 0, policy_version 8360 (0.0008)
+[2025-04-03 14:15:03,937][20447] Updated weights for policy 0, policy_version 8370 (0.0010)
+[2025-04-03 14:15:04,215][12851] Fps is (10 sec: 29081.8, 60 sec: 28808.7, 300 sec: 28838.6). Total num frames: 34287616. Throughput: 0: 7295.8. Samples: 7554390. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:15:04,216][12851] Avg episode reward: [(0, '4.540')]
+[2025-04-03 14:15:05,347][20447] Updated weights for policy 0, policy_version 8380 (0.0011)
+[2025-04-03 14:15:06,747][20447] Updated weights for policy 0, policy_version 8390 (0.0011)
+[2025-04-03 14:15:08,130][20447] Updated weights for policy 0, policy_version 8400 (0.0011)
+[2025-04-03 14:15:09,215][12851] Fps is (10 sec: 29081.0, 60 sec: 28876.7, 300 sec: 28852.5). Total num frames: 34435072. Throughput: 0: 7330.9. Samples: 7598312. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:15:09,217][12851] Avg episode reward: [(0, '4.505')]
+[2025-04-03 14:15:09,526][20447] Updated weights for policy 0, policy_version 8410 (0.0010)
+[2025-04-03 14:15:10,914][20447] Updated weights for policy 0, policy_version 8420 (0.0010)
+[2025-04-03 14:15:12,328][20447] Updated weights for policy 0, policy_version 8430 (0.0009)
+[2025-04-03 14:15:13,731][20447] Updated weights for policy 0, policy_version 8440 (0.0009)
+[2025-04-03 14:15:14,215][12851] Fps is (10 sec: 29490.8, 60 sec: 29081.6, 300 sec: 28866.4). Total num frames: 34582528. Throughput: 0: 7327.4. Samples: 7642390. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:15:14,216][12851] Avg episode reward: [(0, '4.425')]
+[2025-04-03 14:15:15,107][20447] Updated weights for policy 0, policy_version 8450 (0.0008)
+[2025-04-03 14:15:16,509][20447] Updated weights for policy 0, policy_version 8460 (0.0011)
+[2025-04-03 14:15:17,911][20447] Updated weights for policy 0, policy_version 8470 (0.0009)
+[2025-04-03 14:15:19,215][12851] Fps is (10 sec: 29082.2, 60 sec: 29218.2, 300 sec: 28894.2). Total num frames: 34725888. Throughput: 0: 7321.5. Samples: 7664356. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:15:19,216][12851] Avg episode reward: [(0, '4.373')]
+[2025-04-03 14:15:19,325][20447] Updated weights for policy 0, policy_version 8480 (0.0012)
+[2025-04-03 14:15:20,741][20447] Updated weights for policy 0, policy_version 8490 (0.0010)
+[2025-04-03 14:15:22,174][20447] Updated weights for policy 0, policy_version 8500 (0.0010)
+[2025-04-03 14:15:23,582][20447] Updated weights for policy 0, policy_version 8510 (0.0009)
+[2025-04-03 14:15:24,215][12851] Fps is (10 sec: 29081.9, 60 sec: 29286.4, 300 sec: 28949.7). Total num frames: 34873344. Throughput: 0: 7311.9. Samples: 7707848. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:15:24,216][12851] Avg episode reward: [(0, '4.410')]
+[2025-04-03 14:15:24,976][20447] Updated weights for policy 0, policy_version 8520 (0.0011)
+[2025-04-03 14:15:26,382][20447] Updated weights for policy 0, policy_version 8530 (0.0010)
+[2025-04-03 14:15:27,792][20447] Updated weights for policy 0, policy_version 8540 (0.0009)
+[2025-04-03 14:15:29,215][12851] Fps is (10 sec: 29081.6, 60 sec: 29218.2, 300 sec: 28977.5). Total num frames: 35016704. Throughput: 0: 7296.8. Samples: 7751250. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:15:29,216][12851] Avg episode reward: [(0, '4.611')]
+[2025-04-03 14:15:29,235][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000008550_35020800.pth...
+[2025-04-03 14:15:29,238][20447] Updated weights for policy 0, policy_version 8550 (0.0010)
+[2025-04-03 14:15:29,308][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000006852_28065792.pth
+[2025-04-03 14:15:30,666][20447] Updated weights for policy 0, policy_version 8560 (0.0010)
+[2025-04-03 14:15:32,121][20447] Updated weights for policy 0, policy_version 8570 (0.0012)
+[2025-04-03 14:15:33,531][20447] Updated weights for policy 0, policy_version 8580 (0.0012)
+[2025-04-03 14:15:34,215][12851] Fps is (10 sec: 28671.9, 60 sec: 29149.9, 300 sec: 28977.5). Total num frames: 35160064. Throughput: 0: 7286.5. Samples: 7772630. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:15:34,216][12851] Avg episode reward: [(0, '4.264')]
+[2025-04-03 14:15:34,933][20447] Updated weights for policy 0, policy_version 8590 (0.0010)
+[2025-04-03 14:15:36,348][20447] Updated weights for policy 0, policy_version 8600 (0.0011)
+[2025-04-03 14:15:37,794][20447] Updated weights for policy 0, policy_version 8610 (0.0011)
+[2025-04-03 14:15:39,215][12851] Fps is (10 sec: 28671.9, 60 sec: 29081.6, 300 sec: 28977.5). Total num frames: 35303424. Throughput: 0: 7265.6. Samples: 7815692. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:15:39,216][12851] Avg episode reward: [(0, '4.380')]
+[2025-04-03 14:15:39,233][20447] Updated weights for policy 0, policy_version 8620 (0.0011)
+[2025-04-03 14:15:40,644][20447] Updated weights for policy 0, policy_version 8630 (0.0012)
+[2025-04-03 14:15:42,066][20447] Updated weights for policy 0, policy_version 8640 (0.0011)
+[2025-04-03 14:15:43,439][20447] Updated weights for policy 0, policy_version 8650 (0.0013)
+[2025-04-03 14:15:44,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29081.7, 300 sec: 28977.5). Total num frames: 35450880. Throughput: 0: 7268.2. Samples: 7859528. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:15:44,217][12851] Avg episode reward: [(0, '4.481')]
+[2025-04-03 14:15:44,821][20447] Updated weights for policy 0, policy_version 8660 (0.0011)
+[2025-04-03 14:15:46,217][20447] Updated weights for policy 0, policy_version 8670 (0.0012)
+[2025-04-03 14:15:47,599][20447] Updated weights for policy 0, policy_version 8680 (0.0008)
+[2025-04-03 14:15:49,020][20447] Updated weights for policy 0, policy_version 8690 (0.0010)
+[2025-04-03 14:15:49,215][12851] Fps is (10 sec: 29491.2, 60 sec: 29149.9, 300 sec: 28991.4). Total num frames: 35598336. Throughput: 0: 7268.5. Samples: 7881474. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:15:49,216][12851] Avg episode reward: [(0, '4.362')]
+[2025-04-03 14:15:50,460][20447] Updated weights for policy 0, policy_version 8700 (0.0012)
+[2025-04-03 14:15:51,844][20447] Updated weights for policy 0, policy_version 8710 (0.0011)
+[2025-04-03 14:15:53,267][20447] Updated weights for policy 0, policy_version 8720 (0.0011)
+[2025-04-03 14:15:54,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29081.6, 300 sec: 28991.4). Total num frames: 35741696. Throughput: 0: 7261.0. Samples: 7925054. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:15:54,216][12851] Avg episode reward: [(0, '4.654')]
+[2025-04-03 14:15:54,686][20447] Updated weights for policy 0, policy_version 8730 (0.0010)
+[2025-04-03 14:15:56,072][20447] Updated weights for policy 0, policy_version 8740 (0.0010)
+[2025-04-03 14:15:57,482][20447] Updated weights for policy 0, policy_version 8750 (0.0011)
+[2025-04-03 14:15:58,912][20447] Updated weights for policy 0, policy_version 8760 (0.0013)
+[2025-04-03 14:15:59,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29081.6, 300 sec: 29005.2). Total num frames: 35889152. Throughput: 0: 7249.7. Samples: 7968626. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:15:59,217][12851] Avg episode reward: [(0, '4.525')]
+[2025-04-03 14:16:00,354][20447] Updated weights for policy 0, policy_version 8770 (0.0009)
+[2025-04-03 14:16:01,738][20447] Updated weights for policy 0, policy_version 8780 (0.0009)
+[2025-04-03 14:16:03,136][20447] Updated weights for policy 0, policy_version 8790 (0.0011)
+[2025-04-03 14:16:04,215][12851] Fps is (10 sec: 29081.2, 60 sec: 29081.5, 300 sec: 28991.3). Total num frames: 36032512. Throughput: 0: 7243.2. Samples: 7990302. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:16:04,217][12851] Avg episode reward: [(0, '4.446')]
+[2025-04-03 14:16:04,553][20447] Updated weights for policy 0, policy_version 8800 (0.0008)
+[2025-04-03 14:16:05,935][20447] Updated weights for policy 0, policy_version 8810 (0.0009)
+[2025-04-03 14:16:07,435][20447] Updated weights for policy 0, policy_version 8820 (0.0009)
+[2025-04-03 14:16:08,987][20447] Updated weights for policy 0, policy_version 8830 (0.0013)
+[2025-04-03 14:16:09,215][12851] Fps is (10 sec: 28262.2, 60 sec: 28945.1, 300 sec: 28963.6). Total num frames: 36171776. Throughput: 0: 7228.5. Samples: 8033130. Policy #0 lag: (min: 0.0, avg: 1.2, max: 3.0)
+[2025-04-03 14:16:09,218][12851] Avg episode reward: [(0, '4.357')]
+[2025-04-03 14:16:10,477][20447] Updated weights for policy 0, policy_version 8840 (0.0011)
+[2025-04-03 14:16:11,977][20447] Updated weights for policy 0, policy_version 8850 (0.0013)
+[2025-04-03 14:16:13,522][20447] Updated weights for policy 0, policy_version 8860 (0.0012)
+[2025-04-03 14:16:14,215][12851] Fps is (10 sec: 27443.6, 60 sec: 28740.3, 300 sec: 28921.9). Total num frames: 36306944. Throughput: 0: 7165.2. Samples: 8073682. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:14,217][12851] Avg episode reward: [(0, '4.499')]
+[2025-04-03 14:16:15,004][20447] Updated weights for policy 0, policy_version 8870 (0.0014)
+[2025-04-03 14:16:16,503][20447] Updated weights for policy 0, policy_version 8880 (0.0011)
+[2025-04-03 14:16:18,052][20447] Updated weights for policy 0, policy_version 8890 (0.0009)
+[2025-04-03 14:16:19,215][12851] Fps is (10 sec: 27033.3, 60 sec: 28603.6, 300 sec: 28894.1). Total num frames: 36442112. Throughput: 0: 7142.1. Samples: 8094024. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:19,217][12851] Avg episode reward: [(0, '4.336')]
+[2025-04-03 14:16:19,600][20447] Updated weights for policy 0, policy_version 8900 (0.0012)
+[2025-04-03 14:16:21,121][20447] Updated weights for policy 0, policy_version 8910 (0.0011)
+[2025-04-03 14:16:22,671][20447] Updated weights for policy 0, policy_version 8920 (0.0013)
+[2025-04-03 14:16:24,215][12851] Fps is (10 sec: 26623.9, 60 sec: 28330.7, 300 sec: 28838.6). Total num frames: 36573184. Throughput: 0: 7071.0. Samples: 8133886. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:24,217][12851] Avg episode reward: [(0, '4.333')]
+[2025-04-03 14:16:24,222][20447] Updated weights for policy 0, policy_version 8930 (0.0011)
+[2025-04-03 14:16:25,607][20447] Updated weights for policy 0, policy_version 8940 (0.0010)
+[2025-04-03 14:16:27,038][20447] Updated weights for policy 0, policy_version 8950 (0.0010)
+[2025-04-03 14:16:28,438][20447] Updated weights for policy 0, policy_version 8960 (0.0011)
+[2025-04-03 14:16:29,215][12851] Fps is (10 sec: 27853.3, 60 sec: 28398.9, 300 sec: 28852.5). Total num frames: 36720640. Throughput: 0: 7052.1. Samples: 8176872. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:16:29,217][12851] Avg episode reward: [(0, '4.380')]
+[2025-04-03 14:16:29,846][20447] Updated weights for policy 0, policy_version 8970 (0.0009)
+[2025-04-03 14:16:31,232][20447] Updated weights for policy 0, policy_version 8980 (0.0011)
+[2025-04-03 14:16:32,674][20447] Updated weights for policy 0, policy_version 8990 (0.0012)
+[2025-04-03 14:16:34,052][20447] Updated weights for policy 0, policy_version 9000 (0.0012)
+[2025-04-03 14:16:34,215][12851] Fps is (10 sec: 29491.3, 60 sec: 28467.2, 300 sec: 28852.5). Total num frames: 36868096. Throughput: 0: 7051.2. Samples: 8198776. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:16:34,216][12851] Avg episode reward: [(0, '4.237')]
+[2025-04-03 14:16:35,430][20447] Updated weights for policy 0, policy_version 9010 (0.0011)
+[2025-04-03 14:16:36,835][20447] Updated weights for policy 0, policy_version 9020 (0.0011)
+[2025-04-03 14:16:38,257][20447] Updated weights for policy 0, policy_version 9030 (0.0009)
+[2025-04-03 14:16:39,215][12851] Fps is (10 sec: 29081.2, 60 sec: 28467.1, 300 sec: 28838.6). Total num frames: 37011456. Throughput: 0: 7055.6. Samples: 8242556. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:16:39,216][12851] Avg episode reward: [(0, '4.450')]
+[2025-04-03 14:16:39,678][20447] Updated weights for policy 0, policy_version 9040 (0.0010)
+[2025-04-03 14:16:41,057][20447] Updated weights for policy 0, policy_version 9050 (0.0010)
+[2025-04-03 14:16:42,447][20447] Updated weights for policy 0, policy_version 9060 (0.0009)
+[2025-04-03 14:16:43,807][20447] Updated weights for policy 0, policy_version 9070 (0.0011)
+[2025-04-03 14:16:44,216][12851] Fps is (10 sec: 29080.6, 60 sec: 28467.0, 300 sec: 28852.5). Total num frames: 37158912. Throughput: 0: 7066.8. Samples: 8286634. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:16:44,217][12851] Avg episode reward: [(0, '4.180')]
+[2025-04-03 14:16:45,213][20447] Updated weights for policy 0, policy_version 9080 (0.0010)
+[2025-04-03 14:16:46,638][20447] Updated weights for policy 0, policy_version 9090 (0.0011)
+[2025-04-03 14:16:48,064][20447] Updated weights for policy 0, policy_version 9100 (0.0011)
+[2025-04-03 14:16:49,215][12851] Fps is (10 sec: 29492.0, 60 sec: 28467.2, 300 sec: 28852.5). Total num frames: 37306368. Throughput: 0: 7069.9. Samples: 8308446. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:49,216][12851] Avg episode reward: [(0, '4.408')]
+[2025-04-03 14:16:49,454][20447] Updated weights for policy 0, policy_version 9110 (0.0009)
+[2025-04-03 14:16:50,824][20447] Updated weights for policy 0, policy_version 9120 (0.0010)
+[2025-04-03 14:16:52,252][20447] Updated weights for policy 0, policy_version 9130 (0.0011)
+[2025-04-03 14:16:53,668][20447] Updated weights for policy 0, policy_version 9140 (0.0011)
+[2025-04-03 14:16:54,215][12851] Fps is (10 sec: 29082.3, 60 sec: 28467.2, 300 sec: 28838.6). Total num frames: 37449728. Throughput: 0: 7091.1. Samples: 8352228. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:54,217][12851] Avg episode reward: [(0, '4.624')]
+[2025-04-03 14:16:55,078][20447] Updated weights for policy 0, policy_version 9150 (0.0012)
+[2025-04-03 14:16:56,460][20447] Updated weights for policy 0, policy_version 9160 (0.0011)
+[2025-04-03 14:16:57,885][20447] Updated weights for policy 0, policy_version 9170 (0.0012)
+[2025-04-03 14:16:59,215][12851] Fps is (10 sec: 29081.2, 60 sec: 28467.2, 300 sec: 28852.5). Total num frames: 37597184. Throughput: 0: 7163.5. Samples: 8396038. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:16:59,217][12851] Avg episode reward: [(0, '4.516')]
+[2025-04-03 14:16:59,279][20447] Updated weights for policy 0, policy_version 9180 (0.0011)
+[2025-04-03 14:17:00,704][20447] Updated weights for policy 0, policy_version 9190 (0.0010)
+[2025-04-03 14:17:02,081][20447] Updated weights for policy 0, policy_version 9200 (0.0010)
+[2025-04-03 14:17:03,465][20447] Updated weights for policy 0, policy_version 9210 (0.0011)
+[2025-04-03 14:17:04,215][12851] Fps is (10 sec: 29491.2, 60 sec: 28535.5, 300 sec: 28866.4). Total num frames: 37744640. Throughput: 0: 7197.1. Samples: 8417894. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:04,216][12851] Avg episode reward: [(0, '4.483')]
+[2025-04-03 14:17:04,904][20447] Updated weights for policy 0, policy_version 9220 (0.0011)
+[2025-04-03 14:17:06,300][20447] Updated weights for policy 0, policy_version 9230 (0.0008)
+[2025-04-03 14:17:07,691][20447] Updated weights for policy 0, policy_version 9240 (0.0010)
+[2025-04-03 14:17:09,072][20447] Updated weights for policy 0, policy_version 9250 (0.0010)
+[2025-04-03 14:17:09,215][12851] Fps is (10 sec: 29081.8, 60 sec: 28603.8, 300 sec: 28852.5). Total num frames: 37888000. Throughput: 0: 7289.0. Samples: 8461890. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:09,216][12851] Avg episode reward: [(0, '4.390')]
+[2025-04-03 14:17:10,485][20447] Updated weights for policy 0, policy_version 9260 (0.0009)
+[2025-04-03 14:17:11,886][20447] Updated weights for policy 0, policy_version 9270 (0.0011)
+[2025-04-03 14:17:13,281][20447] Updated weights for policy 0, policy_version 9280 (0.0009)
+[2025-04-03 14:17:14,215][12851] Fps is (10 sec: 29081.4, 60 sec: 28808.5, 300 sec: 28866.4). Total num frames: 38035456. Throughput: 0: 7305.1. Samples: 8505604. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:17:14,217][12851] Avg episode reward: [(0, '4.611')]
+[2025-04-03 14:17:14,693][20447] Updated weights for policy 0, policy_version 9290 (0.0011)
+[2025-04-03 14:17:16,093][20447] Updated weights for policy 0, policy_version 9300 (0.0010)
+[2025-04-03 14:17:17,484][20447] Updated weights for policy 0, policy_version 9310 (0.0011)
+[2025-04-03 14:17:18,863][20447] Updated weights for policy 0, policy_version 9320 (0.0010)
+[2025-04-03 14:17:19,215][12851] Fps is (10 sec: 29491.2, 60 sec: 29013.5, 300 sec: 28880.3). Total num frames: 38182912. Throughput: 0: 7309.1. Samples: 8527686. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:19,216][12851] Avg episode reward: [(0, '4.397')]
+[2025-04-03 14:17:20,302][20447] Updated weights for policy 0, policy_version 9330 (0.0011)
+[2025-04-03 14:17:21,693][20447] Updated weights for policy 0, policy_version 9340 (0.0010)
+[2025-04-03 14:17:23,075][20447] Updated weights for policy 0, policy_version 9350 (0.0011)
+[2025-04-03 14:17:24,215][12851] Fps is (10 sec: 29491.6, 60 sec: 29286.4, 300 sec: 28880.3). Total num frames: 38330368. Throughput: 0: 7309.7. Samples: 8571490. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:24,216][12851] Avg episode reward: [(0, '4.223')]
+[2025-04-03 14:17:24,462][20447] Updated weights for policy 0, policy_version 9360 (0.0012)
+[2025-04-03 14:17:25,872][20447] Updated weights for policy 0, policy_version 9370 (0.0010)
+[2025-04-03 14:17:27,277][20447] Updated weights for policy 0, policy_version 9380 (0.0011)
+[2025-04-03 14:17:28,657][20447] Updated weights for policy 0, policy_version 9390 (0.0013)
+[2025-04-03 14:17:29,215][12851] Fps is (10 sec: 29491.1, 60 sec: 29286.4, 300 sec: 28908.0). Total num frames: 38477824. Throughput: 0: 7309.8. Samples: 8615572. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:29,217][12851] Avg episode reward: [(0, '4.406')]
+[2025-04-03 14:17:29,223][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000009394_38477824.pth...
+[2025-04-03 14:17:29,282][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000007700_31539200.pth
+[2025-04-03 14:17:30,066][20447] Updated weights for policy 0, policy_version 9400 (0.0011)
+[2025-04-03 14:17:31,492][20447] Updated weights for policy 0, policy_version 9410 (0.0010)
+[2025-04-03 14:17:32,874][20447] Updated weights for policy 0, policy_version 9420 (0.0008)
+[2025-04-03 14:17:34,215][12851] Fps is (10 sec: 29081.5, 60 sec: 29218.1, 300 sec: 28949.7). Total num frames: 38621184. Throughput: 0: 7307.2. Samples: 8637272. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:17:34,217][12851] Avg episode reward: [(0, '4.355')]
+[2025-04-03 14:17:34,300][20447] Updated weights for policy 0, policy_version 9430 (0.0010)
+[2025-04-03 14:17:35,687][20447] Updated weights for policy 0, policy_version 9440 (0.0012)
+[2025-04-03 14:17:37,065][20447] Updated weights for policy 0, policy_version 9450 (0.0011)
+[2025-04-03 14:17:38,474][20447] Updated weights for policy 0, policy_version 9460 (0.0009)
+[2025-04-03 14:17:39,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29286.5, 300 sec: 28963.6). Total num frames: 38768640. Throughput: 0: 7309.5. Samples: 8681156. Policy #0 lag: (min: 0.0, avg: 1.1, max: 3.0)
+[2025-04-03 14:17:39,216][12851] Avg episode reward: [(0, '4.625')]
+[2025-04-03 14:17:39,903][20447] Updated weights for policy 0, policy_version 9470 (0.0008)
+[2025-04-03 14:17:41,322][20447] Updated weights for policy 0, policy_version 9480 (0.0011)
+[2025-04-03 14:17:42,716][20447] Updated weights for policy 0, policy_version 9490 (0.0011)
+[2025-04-03 14:17:44,148][20447] Updated weights for policy 0, policy_version 9500 (0.0010)
+[2025-04-03 14:17:44,215][12851] Fps is (10 sec: 29081.8, 60 sec: 29218.3, 300 sec: 28963.6). Total num frames: 38912000. Throughput: 0: 7304.9. Samples: 8724758. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:44,216][12851] Avg episode reward: [(0, '4.280')]
+[2025-04-03 14:17:45,536][20447] Updated weights for policy 0, policy_version 9510 (0.0010)
+[2025-04-03 14:17:46,934][20447] Updated weights for policy 0, policy_version 9520 (0.0010)
+[2025-04-03 14:17:48,320][20447] Updated weights for policy 0, policy_version 9530 (0.0012)
+[2025-04-03 14:17:49,215][12851] Fps is (10 sec: 29081.3, 60 sec: 29218.1, 300 sec: 28963.6). Total num frames: 39059456. Throughput: 0: 7306.6. Samples: 8746690. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:49,217][12851] Avg episode reward: [(0, '4.481')]
+[2025-04-03 14:17:49,763][20447] Updated weights for policy 0, policy_version 9540 (0.0010)
+[2025-04-03 14:17:51,129][20447] Updated weights for policy 0, policy_version 9550 (0.0010)
+[2025-04-03 14:17:52,581][20447] Updated weights for policy 0, policy_version 9560 (0.0009)
+[2025-04-03 14:17:53,951][20447] Updated weights for policy 0, policy_version 9570 (0.0009)
+[2025-04-03 14:17:54,215][12851] Fps is (10 sec: 29081.2, 60 sec: 29218.1, 300 sec: 28949.7). Total num frames: 39202816. Throughput: 0: 7300.6. Samples: 8790420. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:54,216][12851] Avg episode reward: [(0, '4.222')]
+[2025-04-03 14:17:55,364][20447] Updated weights for policy 0, policy_version 9580 (0.0009)
+[2025-04-03 14:17:56,746][20447] Updated weights for policy 0, policy_version 9590 (0.0010)
+[2025-04-03 14:17:58,223][20447] Updated weights for policy 0, policy_version 9600 (0.0011)
+[2025-04-03 14:17:59,215][12851] Fps is (10 sec: 28671.9, 60 sec: 29149.8, 300 sec: 28949.7). Total num frames: 39346176. Throughput: 0: 7287.8. Samples: 8833556. Policy #0 lag: (min: 0.0, avg: 1.1, max: 2.0)
+[2025-04-03 14:17:59,217][12851] Avg episode reward: [(0, '4.300')]
+[2025-04-03 14:17:59,695][20447] Updated weights for policy 0, policy_version 9610 (0.0010)
+[2025-04-03 14:18:01,138][20447] Updated weights for policy 0, policy_version 9620 (0.0011)
+[2025-04-03 14:18:02,607][20447] Updated weights for policy 0, policy_version 9630 (0.0011)
+[2025-04-03 14:18:04,131][20447] Updated weights for policy 0, policy_version 9640 (0.0011)
+[2025-04-03 14:18:04,215][12851] Fps is (10 sec: 28262.3, 60 sec: 29013.3, 300 sec: 28921.9). Total num frames: 39485440. Throughput: 0: 7263.4. Samples: 8854538. Policy #0 lag: (min: 0.0, avg: 1.3, max: 2.0)
+[2025-04-03 14:18:04,217][12851] Avg episode reward: [(0, '4.456')]
+[2025-04-03 14:18:05,696][20447] Updated weights for policy 0, policy_version 9650 (0.0012)
+[2025-04-03 14:18:07,271][20447] Updated weights for policy 0, policy_version 9660 (0.0010)
+[2025-04-03 14:18:08,820][20447] Updated weights for policy 0, policy_version 9670 (0.0013)
+[2025-04-03 14:18:09,215][12851] Fps is (10 sec: 27033.9, 60 sec: 28808.5, 300 sec: 28866.4). Total num frames: 39616512. Throughput: 0: 7176.3. Samples: 8894422. Policy #0 lag: (min: 0.0, avg: 1.3, max: 2.0)
+[2025-04-03 14:18:09,217][12851] Avg episode reward: [(0, '4.335')]
+[2025-04-03 14:18:10,400][20447] Updated weights for policy 0, policy_version 9680 (0.0014)
+[2025-04-03 14:18:12,023][20447] Updated weights for policy 0, policy_version 9690 (0.0012)
+[2025-04-03 14:18:13,582][20447] Updated weights for policy 0, policy_version 9700 (0.0011)
+[2025-04-03 14:18:14,215][12851] Fps is (10 sec: 26214.8, 60 sec: 28535.5, 300 sec: 28824.7). Total num frames: 39747584. Throughput: 0: 7058.5. Samples: 8933204. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0)
+[2025-04-03 14:18:14,217][12851] Avg episode reward: [(0, '4.358')]
+[2025-04-03 14:18:15,124][20447] Updated weights for policy 0, policy_version 9710 (0.0016)
+[2025-04-03 14:18:16,709][20447] Updated weights for policy 0, policy_version 9720 (0.0012)
+[2025-04-03 14:18:18,277][20447] Updated weights for policy 0, policy_version 9730 (0.0013)
+[2025-04-03 14:18:19,215][12851] Fps is (10 sec: 26214.2, 60 sec: 28262.3, 300 sec: 28769.2). Total num frames: 39878656. Throughput: 0: 7014.5. Samples: 8952924. Policy #0 lag: (min: 0.0, avg: 1.2, max: 2.0)
+[2025-04-03 14:18:19,217][12851] Avg episode reward: [(0, '4.566')]
+[2025-04-03 14:18:19,797][20447] Updated weights for policy 0, policy_version 9740 (0.0013)
+[2025-04-03 14:18:21,350][20447] Updated weights for policy 0, policy_version 9750 (0.0010)
+[2025-04-03 14:18:22,770][20447] Updated weights for policy 0, policy_version 9760 (0.0010)
+[2025-04-03 14:18:23,793][20429] Stopping Batcher_0...
+[2025-04-03 14:18:23,793][20429] Loop batcher_evt_loop terminating...
+[2025-04-03 14:18:23,793][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000009767_40005632.pth...
+[2025-04-03 14:18:23,794][12851] Component Batcher_0 stopped!
+[2025-04-03 14:18:23,836][20429] Removing /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000008550_35020800.pth
+[2025-04-03 14:18:23,840][20429] Saving /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000009767_40005632.pth...
+[2025-04-03 14:18:23,842][20487] Stopping RolloutWorker_w9...
+[2025-04-03 14:18:23,843][20487] Loop rollout_proc9_evt_loop terminating...
+[2025-04-03 14:18:23,843][12851] Component RolloutWorker_w9 stopped!
+[2025-04-03 14:18:23,847][20488] Stopping RolloutWorker_w10...
+[2025-04-03 14:18:23,847][20449] Stopping RolloutWorker_w1...
+[2025-04-03 14:18:23,848][20488] Loop rollout_proc10_evt_loop terminating...
+[2025-04-03 14:18:23,848][20482] Stopping RolloutWorker_w3...
+[2025-04-03 14:18:23,848][20449] Loop rollout_proc1_evt_loop terminating...
+[2025-04-03 14:18:23,849][20482] Loop rollout_proc3_evt_loop terminating...
+[2025-04-03 14:18:23,847][12851] Component RolloutWorker_w10 stopped!
+[2025-04-03 14:18:23,848][20448] Stopping RolloutWorker_w0...
+[2025-04-03 14:18:23,849][20450] Stopping RolloutWorker_w2...
+[2025-04-03 14:18:23,849][20484] Stopping RolloutWorker_w5...
+[2025-04-03 14:18:23,849][20448] Loop rollout_proc0_evt_loop terminating...
+[2025-04-03 14:18:23,849][20450] Loop rollout_proc2_evt_loop terminating...
+[2025-04-03 14:18:23,849][20484] Loop rollout_proc5_evt_loop terminating...
+[2025-04-03 14:18:23,849][12851] Component RolloutWorker_w1 stopped!
+[2025-04-03 14:18:23,850][20485] Stopping RolloutWorker_w7...
+[2025-04-03 14:18:23,849][20491] Stopping RolloutWorker_w12...
+[2025-04-03 14:18:23,850][20485] Loop rollout_proc7_evt_loop terminating...
+[2025-04-03 14:18:23,850][20483] Stopping RolloutWorker_w4...
+[2025-04-03 14:18:23,850][20491] Loop rollout_proc12_evt_loop terminating...
+[2025-04-03 14:18:23,850][20483] Loop rollout_proc4_evt_loop terminating...
+[2025-04-03 14:18:23,850][20490] Stopping RolloutWorker_w11...
+[2025-04-03 14:18:23,850][20486] Stopping RolloutWorker_w6...
+[2025-04-03 14:18:23,851][20486] Loop rollout_proc6_evt_loop terminating...
+[2025-04-03 14:18:23,851][20490] Loop rollout_proc11_evt_loop terminating...
+[2025-04-03 14:18:23,851][20489] Stopping RolloutWorker_w8...
+[2025-04-03 14:18:23,850][12851] Component RolloutWorker_w3 stopped!
+[2025-04-03 14:18:23,852][20489] Loop rollout_proc8_evt_loop terminating...
+[2025-04-03 14:18:23,851][12851] Component RolloutWorker_w0 stopped!
+[2025-04-03 14:18:23,853][12851] Component RolloutWorker_w2 stopped!
+[2025-04-03 14:18:23,854][12851] Component RolloutWorker_w5 stopped!
+[2025-04-03 14:18:23,855][12851] Component RolloutWorker_w12 stopped!
+[2025-04-03 14:18:23,855][12851] Component RolloutWorker_w7 stopped!
+[2025-04-03 14:18:23,856][12851] Component RolloutWorker_w4 stopped!
+[2025-04-03 14:18:23,857][12851] Component RolloutWorker_w6 stopped!
+[2025-04-03 14:18:23,858][12851] Component RolloutWorker_w11 stopped!
+[2025-04-03 14:18:23,859][12851] Component RolloutWorker_w8 stopped!
+[2025-04-03 14:18:23,896][20429] Stopping LearnerWorker_p0...
+[2025-04-03 14:18:23,897][20429] Loop learner_proc0_evt_loop terminating...
+[2025-04-03 14:18:23,896][12851] Component LearnerWorker_p0 stopped!
+[2025-04-03 14:18:24,004][20447] Weights refcount: 2 0
+[2025-04-03 14:18:24,006][20447] Stopping InferenceWorker_p0-w0...
+[2025-04-03 14:18:24,007][20447] Loop inference_proc0-0_evt_loop terminating...
+[2025-04-03 14:18:24,007][12851] Component InferenceWorker_p0-w0 stopped!
+[2025-04-03 14:18:24,009][12851] Waiting for process learner_proc0 to stop...
+[2025-04-03 14:18:25,397][12851] Waiting for process inference_proc0-0 to join...
+[2025-04-03 14:18:25,399][12851] Waiting for process rollout_proc0 to join...
+[2025-04-03 14:18:25,399][12851] Waiting for process rollout_proc1 to join...
+[2025-04-03 14:18:25,400][12851] Waiting for process rollout_proc2 to join...
+[2025-04-03 14:18:25,400][12851] Waiting for process rollout_proc3 to join...
+[2025-04-03 14:18:25,402][12851] Waiting for process rollout_proc4 to join...
+[2025-04-03 14:18:25,402][12851] Waiting for process rollout_proc5 to join...
+[2025-04-03 14:18:25,403][12851] Waiting for process rollout_proc6 to join...
+[2025-04-03 14:18:25,404][12851] Waiting for process rollout_proc7 to join...
+[2025-04-03 14:18:25,404][12851] Waiting for process rollout_proc8 to join...
+[2025-04-03 14:18:25,405][12851] Waiting for process rollout_proc9 to join...
+[2025-04-03 14:18:25,406][12851] Waiting for process rollout_proc10 to join...
+[2025-04-03 14:18:25,407][12851] Waiting for process rollout_proc11 to join...
+[2025-04-03 14:18:25,407][12851] Waiting for process rollout_proc12 to join...
+[2025-04-03 14:18:25,408][12851] Batcher 0 profile tree view:
+batching: 130.7032, releasing_batches: 0.2264
+[2025-04-03 14:18:25,409][12851] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0000
+  wait_policy_total: 11.8453
+update_model: 20.8259
+  weight_update: 0.0011
+one_step: 0.0021
+  handle_policy_step: 1175.4087
+    deserialize: 45.5125, stack: 6.2705, obs_to_device_normalize: 270.2457, forward: 450.7194, send_messages: 135.8433
+    prepare_outputs: 230.8784
+      to_cpu: 188.8414
+[2025-04-03 14:18:25,410][12851] Learner 0 profile tree view:
+misc: 0.0360, prepare_batch: 108.3024
+train: 263.1475
+  epoch_init: 0.0392, minibatch_init: 0.0504, losses_postprocess: 2.8280, kl_divergence: 3.2421, after_optimizer: 3.6350
+  calculate_losses: 94.5120
+    losses_init: 0.0216, forward_head: 5.9900, bptt_initial: 64.7990, tail: 4.2702, advantages_returns: 1.1590, losses: 8.6728
+    bptt: 8.3519
+      bptt_forward_core: 7.9720
+  update: 156.1543
+    clip: 5.5173
+[2025-04-03 14:18:25,410][12851] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.5855, enqueue_policy_requests: 33.1711, env_step: 678.4641, overhead: 27.8859, complete_rollouts: 1.1997
+save_policy_outputs: 39.2901
+  split_output_tensors: 13.2301
+[2025-04-03 14:18:25,411][12851] RolloutWorker_w12 profile tree view:
+wait_for_trajectories: 0.5872, enqueue_policy_requests: 32.5725, env_step: 679.8059, overhead: 28.5253, complete_rollouts: 1.1910
+save_policy_outputs: 39.3413
+  split_output_tensors: 13.4781
+[2025-04-03 14:18:25,412][12851] Loop Runner_EvtLoop terminating...
+[2025-04-03 14:18:25,413][12851] Runner profile tree view:
+main_loop: 1254.7503
+[2025-04-03 14:18:25,413][12851] Collected {0: 40005632}, FPS: 28684.2
+[2025-04-03 14:44:49,269][12851] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 14:44:49,271][12851] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 14:44:49,272][12851] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 14:44:49,272][12851] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 14:44:49,273][12851] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 14:44:49,274][12851] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 14:44:49,275][12851] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 14:44:49,275][12851] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 14:44:49,276][12851] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2025-04-03 14:44:49,276][12851] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2025-04-03 14:44:49,277][12851] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 14:44:49,278][12851] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 14:44:49,278][12851] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 14:44:49,279][12851] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 14:44:49,279][12851] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 14:44:49,302][12851] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 14:44:49,305][12851] RunningMeanStd input shape: (1,)
+[2025-04-03 14:44:49,330][12851] ConvEncoder: input_channels=3
+[2025-04-03 14:44:49,378][12851] Conv encoder output size: 512
+[2025-04-03 14:44:49,380][12851] Policy head output size: 512
+[2025-04-03 14:44:49,426][12851] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000009767_40005632.pth...
+[2025-04-03 14:44:49,951][12851] Num frames 100...
+[2025-04-03 14:44:50,168][12851] Num frames 200...
+[2025-04-03 14:44:50,323][12851] Num frames 300...
+[2025-04-03 14:44:50,436][12851] Num frames 400...
+[2025-04-03 14:44:50,562][12851] Num frames 500...
+[2025-04-03 14:44:50,666][12851] Avg episode rewards: #0: 7.440, true rewards: #0: 5.440
+[2025-04-03 14:44:50,667][12851] Avg episode reward: 7.440, avg true_objective: 5.440
+[2025-04-03 14:44:50,750][12851] Num frames 600...
+[2025-04-03 14:44:50,884][12851] Num frames 700...
+[2025-04-03 14:44:51,013][12851] Num frames 800...
+[2025-04-03 14:44:51,140][12851] Num frames 900...
+[2025-04-03 14:44:51,311][12851] Avg episode rewards: #0: 6.460, true rewards: #0: 4.960
+[2025-04-03 14:44:51,312][12851] Avg episode reward: 6.460, avg true_objective: 4.960
+[2025-04-03 14:44:51,324][12851] Num frames 1000...
+[2025-04-03 14:44:51,459][12851] Num frames 1100...
+[2025-04-03 14:44:51,595][12851] Num frames 1200...
+[2025-04-03 14:44:51,723][12851] Num frames 1300...
+[2025-04-03 14:44:51,859][12851] Num frames 1400...
+[2025-04-03 14:44:51,923][12851] Avg episode rewards: #0: 6.360, true rewards: #0: 4.693
+[2025-04-03 14:44:51,924][12851] Avg episode reward: 6.360, avg true_objective: 4.693
+[2025-04-03 14:44:52,053][12851] Num frames 1500...
+[2025-04-03 14:44:52,183][12851] Num frames 1600...
+[2025-04-03 14:44:52,307][12851] Num frames 1700...
+[2025-04-03 14:44:52,480][12851] Avg episode rewards: #0: 5.730, true rewards: #0: 4.480
+[2025-04-03 14:44:52,481][12851] Avg episode reward: 5.730, avg true_objective: 4.480
+[2025-04-03 14:44:52,492][12851] Num frames 1800...
+[2025-04-03 14:44:52,621][12851] Num frames 1900...
+[2025-04-03 14:44:52,757][12851] Num frames 2000...
+[2025-04-03 14:44:52,870][12851] Num frames 2100...
+[2025-04-03 14:44:53,023][12851] Avg episode rewards: #0: 5.352, true rewards: #0: 4.352
+[2025-04-03 14:44:53,024][12851] Avg episode reward: 5.352, avg true_objective: 4.352
+[2025-04-03 14:44:53,066][12851] Num frames 2200...
+[2025-04-03 14:44:53,201][12851] Num frames 2300...
+[2025-04-03 14:44:53,328][12851] Num frames 2400...
+[2025-04-03 14:44:53,419][12851] Avg episode rewards: #0: 4.887, true rewards: #0: 4.053
+[2025-04-03 14:44:53,421][12851] Avg episode reward: 4.887, avg true_objective: 4.053
+[2025-04-03 14:44:53,517][12851] Num frames 2500...
+[2025-04-03 14:44:53,647][12851] Num frames 2600...
+[2025-04-03 14:44:53,766][12851] Num frames 2700...
+[2025-04-03 14:44:53,891][12851] Num frames 2800...
+[2025-04-03 14:44:54,052][12851] Avg episode rewards: #0: 4.971, true rewards: #0: 4.114
+[2025-04-03 14:44:54,053][12851] Avg episode reward: 4.971, avg true_objective: 4.114
+[2025-04-03 14:44:54,081][12851] Num frames 2900...
+[2025-04-03 14:44:54,199][12851] Num frames 3000...
+[2025-04-03 14:44:54,329][12851] Num frames 3100...
+[2025-04-03 14:44:54,430][12851] Avg episode rewards: #0: 4.670, true rewards: #0: 3.920
+[2025-04-03 14:44:54,431][12851] Avg episode reward: 4.670, avg true_objective: 3.920
+[2025-04-03 14:44:54,517][12851] Num frames 3200...
+[2025-04-03 14:44:54,641][12851] Num frames 3300...
+[2025-04-03 14:44:54,758][12851] Num frames 3400...
+[2025-04-03 14:44:54,884][12851] Num frames 3500...
+[2025-04-03 14:44:55,036][12851] Avg episode rewards: #0: 4.760, true rewards: #0: 3.982
+[2025-04-03 14:44:55,037][12851] Avg episode reward: 4.760, avg true_objective: 3.982
+[2025-04-03 14:44:55,063][12851] Num frames 3600...
+[2025-04-03 14:44:55,200][12851] Num frames 3700...
+[2025-04-03 14:44:55,321][12851] Num frames 3800...
+[2025-04-03 14:44:55,444][12851] Num frames 3900...
+[2025-04-03 14:44:55,584][12851] Avg episode rewards: #0: 4.668, true rewards: #0: 3.968
+[2025-04-03 14:44:55,586][12851] Avg episode reward: 4.668, avg true_objective: 3.968
+[2025-04-03 14:44:59,625][12851] Replay video saved to /home/haricot/dev/rl-unit8/train_dir/default_experiment/replay.mp4!
+[2025-04-03 14:46:03,719][12851] Loading existing experiment configuration from /home/haricot/dev/rl-unit8/train_dir/default_experiment/config.json
+[2025-04-03 14:46:03,721][12851] Overriding arg 'num_workers' with value 1 passed from command line
+[2025-04-03 14:46:03,721][12851] Adding new argument 'no_render'=True that is not in the saved config file!
+[2025-04-03 14:46:03,722][12851] Adding new argument 'save_video'=True that is not in the saved config file!
+[2025-04-03 14:46:03,723][12851] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2025-04-03 14:46:03,724][12851] Adding new argument 'video_name'=None that is not in the saved config file!
+[2025-04-03 14:46:03,724][12851] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2025-04-03 14:46:03,725][12851] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2025-04-03 14:46:03,726][12851] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2025-04-03 14:46:03,726][12851] Adding new argument 'hf_repository'='Haricot24601/rl_course_vizdoom_health_gathering_supreme_2' that is not in the saved config file!
+[2025-04-03 14:46:03,727][12851] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2025-04-03 14:46:03,728][12851] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2025-04-03 14:46:03,728][12851] Adding new argument 'train_script'=None that is not in the saved config file!
+[2025-04-03 14:46:03,729][12851] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2025-04-03 14:46:03,730][12851] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2025-04-03 14:46:03,742][12851] RunningMeanStd input shape: (3, 72, 128)
+[2025-04-03 14:46:03,743][12851] RunningMeanStd input shape: (1,)
+[2025-04-03 14:46:03,753][12851] ConvEncoder: input_channels=3
+[2025-04-03 14:46:03,778][12851] Conv encoder output size: 512
+[2025-04-03 14:46:03,779][12851] Policy head output size: 512
+[2025-04-03 14:46:03,818][12851] Loading state from checkpoint /home/haricot/dev/rl-unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000009767_40005632.pth...
+[2025-04-03 14:46:04,326][12851] Num frames 100...
+[2025-04-03 14:46:04,513][12851] Num frames 200...
+[2025-04-03 14:46:04,642][12851] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
+[2025-04-03 14:46:04,644][12851] Avg episode reward: 2.560, avg true_objective: 2.560
+[2025-04-03 14:46:04,704][12851] Num frames 300...
+[2025-04-03 14:46:04,829][12851] Num frames 400...
+[2025-04-03 14:46:04,958][12851] Num frames 500...
+[2025-04-03 14:46:05,090][12851] Num frames 600...
+[2025-04-03 14:46:05,192][12851] Avg episode rewards: #0: 3.200, true rewards: #0: 3.200
+[2025-04-03 14:46:05,194][12851] Avg episode reward: 3.200, avg true_objective: 3.200
+[2025-04-03 14:46:05,270][12851] Num frames 700...
+[2025-04-03 14:46:05,394][12851] Num frames 800...
+[2025-04-03 14:46:05,507][12851] Num frames 900...
+[2025-04-03 14:46:05,627][12851] Num frames 1000...
+[2025-04-03 14:46:05,710][12851] Avg episode rewards: #0: 3.413, true rewards: #0: 3.413
+[2025-04-03 14:46:05,713][12851] Avg episode reward: 3.413, avg true_objective: 3.413
+[2025-04-03 14:46:05,808][12851] Num frames 1100...
+[2025-04-03 14:46:05,929][12851] Num frames 1200...
+[2025-04-03 14:46:06,049][12851] Num frames 1300...
+[2025-04-03 14:46:06,159][12851] Num frames 1400...
+[2025-04-03 14:46:06,222][12851] Avg episode rewards: #0: 3.520, true rewards: #0: 3.520
+[2025-04-03 14:46:06,224][12851] Avg episode reward: 3.520, avg true_objective: 3.520
+[2025-04-03 14:46:06,349][12851] Num frames 1500...
+[2025-04-03 14:46:06,473][12851] Num frames 1600...
+[2025-04-03 14:46:06,598][12851] Num frames 1700...
+[2025-04-03 14:46:06,764][12851] Avg episode rewards: #0: 3.584, true rewards: #0: 3.584
+[2025-04-03 14:46:06,765][12851] Avg episode reward: 3.584, avg true_objective: 3.584
+[2025-04-03 14:46:06,776][12851] Num frames 1800...
+[2025-04-03 14:46:06,899][12851] Num frames 1900...
+[2025-04-03 14:46:07,023][12851] Num frames 2000...
+[2025-04-03 14:46:07,141][12851] Num frames 2100...
+[2025-04-03 14:46:07,284][12851] Avg episode rewards: #0: 3.627, true rewards: #0: 3.627
+[2025-04-03 14:46:07,286][12851] Avg episode reward: 3.627, avg true_objective: 3.627
+[2025-04-03 14:46:07,321][12851] Num frames 2200...
+[2025-04-03 14:46:07,448][12851] Num frames 2300...
+[2025-04-03 14:46:07,575][12851] Num frames 2400...
+[2025-04-03 14:46:07,692][12851] Avg episode rewards: #0: 3.500, true rewards: #0: 3.500
+[2025-04-03 14:46:07,693][12851] Avg episode reward: 3.500, avg true_objective: 3.500
+[2025-04-03 14:46:07,758][12851] Num frames 2500...
+[2025-04-03 14:46:07,890][12851] Num frames 2600...
+[2025-04-03 14:46:08,013][12851] Num frames 2700...
+[2025-04-03 14:46:08,137][12851] Num frames 2800...
+[2025-04-03 14:46:08,310][12851] Avg episode rewards: #0: 3.748, true rewards: #0: 3.622
+[2025-04-03 14:46:08,313][12851] Avg episode reward: 3.748, avg true_objective: 3.622
+[2025-04-03 14:46:08,316][12851] Num frames 2900...
+[2025-04-03 14:46:08,445][12851] Num frames 3000...
+[2025-04-03 14:46:08,573][12851] Num frames 3100...
+[2025-04-03 14:46:08,696][12851] Num frames 3200...
+[2025-04-03 14:46:08,823][12851] Num frames 3300...
+[2025-04-03 14:46:08,949][12851] Avg episode rewards: #0: 3.940, true rewards: #0: 3.718
+[2025-04-03 14:46:08,949][12851] Avg episode reward: 3.940, avg true_objective: 3.718
+[2025-04-03 14:46:09,023][12851] Num frames 3400...
+[2025-04-03 14:46:09,146][12851] Num frames 3500...
+[2025-04-03 14:46:09,274][12851] Num frames 3600...
+[2025-04-03 14:46:09,396][12851] Num frames 3700...
+[2025-04-03 14:46:09,570][12851] Avg episode rewards: #0: 4.094, true rewards: #0: 3.794
+[2025-04-03 14:46:09,572][12851] Avg episode reward: 4.094, avg true_objective: 3.794
+[2025-04-03 14:46:13,483][12851] Replay video saved to /home/haricot/dev/rl-unit8/train_dir/default_experiment/replay.mp4!