Upload folder using huggingface_hub

README.md

@@ -1,21 +1,23 @@
 ---
 tags:
-- LunarLander-v3
+- LunarLander-v2
 - ppo
 - reinforcement-learning
 - custom-implementation
+- deep-rl-course
+- gymnasium
 model_index:
 - name: PPO (from scratch)
   results:
   - task:
       type: reinforcement-learning
     dataset:
-      name: LunarLander-v3
-      type: LunarLander-v3
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -26.96 +/- 97.17
+      value: -14.47 +/- 68.73
 ---
-# PPO Agent playing LunarLander-v3
+# PPO Agent playing LunarLander-v2
 
-This is a trained model of a PPO agent playing LunarLander-v3 (trained from scratch).
+This is a trained model of a PPO agent playing LunarLander-v2 (trained from scratch).

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a332ef0522df4b7c524290366e457c30b2dd348a69845ab129cae6ecdc37cda
-size 126560
+oid sha256:302707fd3a02e30d75bc41dbe8d49400377b092904e1a42c0b877337b28b934d
+size 148950

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": -26.959697760446677, "std_reward": 97.16784758036188, "eval_datetime": "2026-03-26T13:03:59.076629"}
+{"env_id": "LunarLander-v3", "mean_reward": -14.468979832827847, "std_reward": 68.73117029185856, "eval_datetime": "2026-03-26T22:23:13.195682"}