{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4060355424880981, "min": 1.4060355424880981, "max": 1.428407073020935, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72928.25, "min": 68553.6171875, "max": 75391.15625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.20980392156862, "min": 97.14509803921568, "max": 406.81451612903226, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49577.0, "min": 49145.0, "max": 50445.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999993.0, "min": 49863.0, "max": 1999993.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999993.0, "min": 49863.0, "max": 1999993.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.327410936355591, "min": 0.04147357493638992, "max": 2.4123694896698, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1184.6522216796875, "min": 5.101249694824219, "max": 1187.4853515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5824769536263816, "min": 1.907672691393674, "max": 3.9674128723585143, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1823.4807693958282, "min": 234.6437410414219, "max": 1932.1300688385963, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5824769536263816, "min": 1.907672691393674, "max": 3.9674128723585143, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1823.4807693958282, "min": 234.6437410414219, "max": 1932.1300688385963, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0159702696352421, "min": 0.0126372866613868, "max": 0.02070225770585239, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0319405392704842, "min": 0.0252745733227736, "max": 0.06210677311755717, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05040423981845379, "min": 0.022069264544794957, "max": 0.06453623293588559, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10080847963690757, "min": 0.044138529089589915, "max": 0.17037474339207012, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.410323529925012e-06, "min": 4.410323529925012e-06, "max": 0.00029537085154305, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.820647059850023e-06, "min": 8.820647059850023e-06, "max": 0.0008442082685972498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10147007499999999, "min": 0.10147007499999999, "max": 0.19845694999999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20294014999999999, "min": 0.20294014999999999, "max": 0.5814027500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.335674250000021e-05, "min": 8.335674250000021e-05, "max": 0.0049230018050000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016671348500000042, "min": 0.00016671348500000042, "max": 0.014071997225, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741478439", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/burzilov/.cache/pypoetry/virtualenvs/deep-rl-class-PXRflMbD-py3.10/bin/mlagents-learn ./Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0", "mlagents_envs_version": "1.1.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1741479839" }, "total": 1399.7768977349988, "count": 1, "self": 0.21738697899854742, "children": { "run_training.setup": { "total": 0.014250051004637498, "count": 1, "self": 0.014250051004637498 }, "TrainerController.start_learning": { "total": 1399.5452607049956, "count": 1, "self": 2.3054460391722387, "children": { "TrainerController._reset_env": { "total": 1.6224144529987825, "count": 1, "self": 1.6224144529987825 }, "TrainerController.advance": { "total": 1395.5489300278205, "count": 231409, "self": 2.113867466672673, "children": { "env_step": { "total": 1164.1685143097493, "count": 231409, "self": 736.8209895096661, "children": { "SubprocessEnvManager._take_step": { "total": 425.7820724477351, "count": 231409, "self": 8.13147407669021, "children": { "TorchPolicy.evaluate": { "total": 417.6505983710449, "count": 223088, "self": 417.6505983710449 } } }, "workers": { "total": 1.5654523523480748, "count": 231409, "self": 0.0, "children": { "worker_root": { "total": 1394.5692830350745, "count": 231409, "is_parallel": true, "self": 776.6078301977032, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00043196300248382613, "count": 1, "is_parallel": true, "self": 0.00010844600910786539, "children": { "_process_rank_one_or_two_observation": { "total": 0.00032351699337596074, "count": 2, "is_parallel": true, "self": 0.00032351699337596074 } } }, "UnityEnvironment.step": { "total": 0.01119381700118538, "count": 1, "is_parallel": true, "self": 9.159799083136022e-05, "children": { "UnityEnvironment._generate_step_input": { "total": 7.066300167934969e-05, "count": 1, "is_parallel": true, "self": 7.066300167934969e-05 }, "communicator.exchange": { "total": 0.010836910005309619, "count": 1, "is_parallel": true, "self": 0.010836910005309619 }, "steps_from_proto": { "total": 0.000194646003365051, "count": 1, "is_parallel": true, "self": 4.7781002649571747e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00014686500071547925, "count": 2, "is_parallel": true, "self": 0.00014686500071547925 } } } } } } }, "UnityEnvironment.step": { "total": 617.9614528373713, "count": 231408, "is_parallel": true, "self": 12.127300653410202, "children": { "UnityEnvironment._generate_step_input": { "total": 19.794466781073424, "count": 231408, "is_parallel": true, "self": 19.794466781073424 }, "communicator.exchange": { "total": 560.6388330302361, "count": 231408, "is_parallel": true, "self": 560.6388330302361 }, "steps_from_proto": { "total": 25.40085237265157, "count": 231408, "is_parallel": true, "self": 8.08674812495883, "children": { "_process_rank_one_or_two_observation": { "total": 17.31410424769274, "count": 462816, "is_parallel": true, "self": 17.31410424769274 } } } } } } } } } } }, "trainer_advance": { "total": 229.2665482513985, "count": 231409, "self": 3.4441442664683564, "children": { "process_trajectory": { "total": 83.84390328194422, "count": 231409, "self": 83.11251818194432, "children": { "RLTrainer._checkpoint": { "total": 0.7313850999998976, "count": 10, "self": 0.7313850999998976 } } }, "_update_policy": { "total": 141.9785007029859, "count": 96, "self": 84.60696279911645, "children": { "TorchPPOOptimizer.update": { "total": 57.371537903869466, "count": 2880, "self": 57.371537903869466 } } } } } } }, "trainer_threads": { "total": 4.1400198824703693e-07, "count": 1, "self": 4.1400198824703693e-07 }, "TrainerController._save_models": { "total": 0.06846977100212825, "count": 1, "self": 0.0008183379977708682, "children": { "RLTrainer._checkpoint": { "total": 0.06765143300435739, "count": 1, "self": 0.06765143300435739 } } } } } } }