{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5712461471557617, "min": 1.518694519996643, "max": 3.295703172683716, "count": 1651 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31223.802734375, "min": 13763.791015625, "max": 112395.0, "count": 1651 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 74.26865671641791, "min": 42.584070796460175, "max": 999.0, "count": 1651 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19904.0, "min": 6100.0, "max": 27820.0, "count": 1651 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1853.880750363968, "min": 1197.5826543751496, "max": 1869.6279759810832, "count": 1648 }, "SoccerTwos.Self-play.ELO.sum": { "value": 248420.02054877172, "min": 2399.999868405824, "max": 399275.79305641016, "count": 1648 }, "SoccerTwos.Step.mean": { "value": 16509962.0, "min": 9826.0, "max": 16509962.0, "count": 1651 }, "SoccerTwos.Step.sum": { "value": 16509962.0, "min": 9826.0, "max": 16509962.0, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02508429065346718, "min": -0.11061567813158035, "max": 0.15488314628601074, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.3362107276916504, "min": -17.79076385498047, "max": 24.440296173095703, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02802651934325695, "min": -0.11210204660892487, "max": 0.1613268107175827, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.727527141571045, "min": -17.466007232666016, "max": 24.463085174560547, "count": 1651 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1651 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.29630676337650846, "min": -0.5714285714285714, "max": 0.5708780543106359, "count": 1651 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 39.40879952907562, "min": -61.7979998588562, "max": 53.049999833106995, "count": 1651 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.29630676337650846, "min": -0.5714285714285714, "max": 0.5708780543106359, "count": 1651 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 39.40879952907562, "min": -61.7979998588562, "max": 53.049999833106995, "count": 1651 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1651 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1651 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013763741419340173, "min": 0.008955371444183886, "max": 0.023560189917528382, "count": 799 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013763741419340173, "min": 0.008955371444183886, "max": 0.023560189917528382, "count": 799 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09360008810957272, "min": 0.0004480640447582118, "max": 0.11776254152258238, "count": 799 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09360008810957272, "min": 0.0004480640447582118, "max": 0.11776254152258238, "count": 799 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0955612560113271, "min": 0.0004502187919570133, "max": 0.11994084765513738, "count": 799 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0955612560113271, "min": 0.0004502187919570133, "max": 0.11994084765513738, "count": 799 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 799 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 799 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 799 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 799 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 799 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 799 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726421259", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/mihofer/Repos/HuggingFaceRLCourse/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=soccertwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726480591" }, "total": 59331.898198616, "count": 1, "self": 0.7195684949983843, "children": { "run_training.setup": { "total": 0.029556982000030985, "count": 1, "self": 0.029556982000030985 }, "TrainerController.start_learning": { "total": 59331.149073139, "count": 1, "self": 24.495702187014103, "children": { "TrainerController._reset_env": { "total": 3.72390110802894, "count": 83, "self": 3.72390110802894 }, "TrainerController.advance": { "total": 59302.686459513956, "count": 1129961, "self": 26.54190119104169, "children": { "env_step": { "total": 35535.1876863446, "count": 1129961, "self": 32235.42121499589, "children": { "SubprocessEnvManager._take_step": { "total": 3284.5690528255964, "count": 1129961, "self": 150.89068069127643, "children": { "TorchPolicy.evaluate": { "total": 3133.67837213432, "count": 2077278, "self": 3133.67837213432 } } }, "workers": { "total": 15.197418523115402, "count": 1129961, "self": 0.0, "children": { "worker_root": { "total": 59263.01548038053, "count": 1129961, "is_parallel": true, "self": 29843.263699950516, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002963484000019889, "count": 2, "is_parallel": true, "self": 0.0014622549999785406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015012290000413486, "count": 8, "is_parallel": true, "self": 0.0015012290000413486 } } }, "UnityEnvironment.step": { "total": 0.03238774999999805, "count": 1, "is_parallel": true, "self": 0.0004703000001882174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003868709998187114, "count": 1, "is_parallel": true, "self": 0.0003868709998187114 }, "communicator.exchange": { "total": 0.03017076200012525, "count": 1, "is_parallel": true, "self": 0.03017076200012525 }, "steps_from_proto": { "total": 0.0013598169998658705, "count": 2, "is_parallel": true, "self": 0.0003068670000629936, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010529499998028768, "count": 8, "is_parallel": true, "self": 0.0010529499998028768 } } } } } } }, "UnityEnvironment.step": { "total": 29419.589919785, "count": 1129960, "is_parallel": true, "self": 631.794396040681, "children": { "UnityEnvironment._generate_step_input": { "total": 359.3457694350325, "count": 1129960, "is_parallel": true, "self": 359.3457694350325 }, "communicator.exchange": { "total": 26608.22457511589, "count": 1129960, "is_parallel": true, "self": 26608.22457511589 }, "steps_from_proto": { "total": 1820.2251791933943, "count": 2259920, "is_parallel": true, "self": 384.1397032106197, "children": { "_process_rank_one_or_two_observation": { "total": 1436.0854759827746, "count": 9039680, "is_parallel": true, "self": 1436.0854759827746 } } } } }, "steps_from_proto": { "total": 0.16186064501061992, "count": 164, "is_parallel": true, "self": 0.035085109133433434, "children": { "_process_rank_one_or_two_observation": { "total": 0.12677553587718648, "count": 656, "is_parallel": true, "self": 0.12677553587718648 } } } } } } } } }, "trainer_advance": { "total": 23740.956871978313, "count": 1129961, "self": 191.76520786236506, "children": { "process_trajectory": { "total": 3288.889129002902, "count": 1129961, "self": 3284.37206933092, "children": { "RLTrainer._checkpoint": { "total": 4.5170596719817695, "count": 33, "self": 4.5170596719817695 } } }, "_update_policy": { "total": 20260.302535113045, "count": 799, "self": 1778.8690876569344, "children": { "TorchPOCAOptimizer.update": { "total": 18481.43344745611, "count": 23979, "self": 18481.43344745611 } } } } } } }, "trainer_threads": { "total": 1.3230019249022007e-06, "count": 1, "self": 1.3230019249022007e-06 }, "TrainerController._save_models": { "total": 0.24300900699745398, "count": 1, "self": 0.0020729829993797466, "children": { "RLTrainer._checkpoint": { "total": 0.24093602399807423, "count": 1, "self": 0.24093602399807423 } } } } } } }