{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.2512972354888916, "min": 2.2299022674560547, "max": 3.2957186698913574, "count": 562 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45602.27734375, "min": 210.48744201660156, "max": 117762.34375, "count": 562 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 51.55789473684211, "min": 43.482142857142854, "max": 999.0, "count": 562 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19592.0, "min": 3112.0, "max": 31968.0, "count": 562 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1431.894787408498, "min": 1177.37739805464, "max": 1441.8620239325535, "count": 449 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272060.0096076146, "min": 2354.75479610928, "max": 306835.3105804471, "count": 449 }, "SoccerTwos.Step.mean": { "value": 5619995.0, "min": 9840.0, "max": 5619995.0, "count": 562 }, "SoccerTwos.Step.sum": { "value": 5619995.0, "min": 9840.0, "max": 5619995.0, "count": 562 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.008535241708159447, "min": -0.07643411308526993, "max": 0.1327708512544632, "count": 562 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.6216959953308105, "min": -12.117111206054688, "max": 25.359233856201172, "count": 562 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006365294102579355, "min": -0.07697104662656784, "max": 0.13355323672294617, "count": 562 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.2094058990478516, "min": -12.854165077209473, "max": 25.508668899536133, "count": 562 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 562 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 562 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06011052790441011, "min": -0.5714285714285714, "max": 0.4621249958872795, "count": 562 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.421000301837921, "min": -40.99080008268356, "max": 45.73100024461746, "count": 562 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06011052790441011, "min": -0.5714285714285714, "max": 0.4621249958872795, "count": 562 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.421000301837921, "min": -40.99080008268356, "max": 45.73100024461746, "count": 562 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 562 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 562 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018468388903420417, "min": 0.010478435871967425, "max": 0.024917255611702178, "count": 264 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018468388903420417, "min": 0.010478435871967425, "max": 0.024917255611702178, "count": 264 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08638501664002736, "min": 4.068811290854531e-08, "max": 0.1062912255525589, "count": 264 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08638501664002736, "min": 4.068811290854531e-08, "max": 0.1062912255525589, "count": 264 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08870537256201108, "min": 4.0923209236135943e-08, "max": 0.10939665660262107, "count": 264 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08870537256201108, "min": 4.0923209236135943e-08, "max": 0.10939665660262107, "count": 264 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 264 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 264 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 264 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 264 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 264 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 264 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702049216", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/dbailleu/.local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.22.3", "end_time_seconds": "1702070490" }, "total": 21274.4086999, "count": 1, "self": 0.16768681899702642, "children": { "run_training.setup": { "total": 0.01036884600034682, "count": 1, "self": 0.01036884600034682 }, "TrainerController.start_learning": { "total": 21274.230644235, "count": 1, "self": 7.4248600445753254, "children": { "TrainerController._reset_env": { "total": 2.4546099879880785, "count": 29, "self": 2.4546099879880785 }, "TrainerController.advance": { "total": 21264.258678789443, "count": 372560, "self": 9.100830649873387, "children": { "env_step": { "total": 8574.15538607199, "count": 372560, "self": 7400.381202805122, "children": { "SubprocessEnvManager._take_step": { "total": 1168.4869949782988, "count": 372560, "self": 51.36865540101644, "children": { "TorchPolicy.evaluate": { "total": 1117.1183395772823, "count": 717920, "self": 1117.1183395772823 } } }, "workers": { "total": 5.287188288570178, "count": 372560, "self": 0.0, "children": { "worker_root": { "total": 21231.55430940061, "count": 372560, "is_parallel": true, "self": 14756.326627073799, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002743323999311542, "count": 2, "is_parallel": true, "self": 0.0005649750019074418, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021783489974041004, "count": 8, "is_parallel": true, "self": 0.0021783489974041004 } } }, "UnityEnvironment.step": { "total": 0.029804314999637427, "count": 1, "is_parallel": true, "self": 0.00036474899388849735, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009311610010627192, "count": 1, "is_parallel": true, "self": 0.0009311610010627192 }, "communicator.exchange": { "total": 0.027411934002884664, "count": 1, "is_parallel": true, "self": 0.027411934002884664 }, "steps_from_proto": { "total": 0.0010964710018015467, "count": 2, "is_parallel": true, "self": 0.00023595700622536242, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008605139955761842, "count": 8, "is_parallel": true, "self": 0.0008605139955761842 } } } } } } }, "UnityEnvironment.step": { "total": 6475.1886665398015, "count": 372559, "is_parallel": true, "self": 176.72478310902443, "children": { "UnityEnvironment._generate_step_input": { "total": 253.02448767446913, "count": 372559, "is_parallel": true, "self": 253.02448767446913 }, "communicator.exchange": { "total": 5509.755959868915, "count": 372559, "is_parallel": true, "self": 5509.755959868915 }, "steps_from_proto": { "total": 535.683435887393, "count": 745118, "is_parallel": true, "self": 113.83367876522607, "children": { "_process_rank_one_or_two_observation": { "total": 421.8497571221669, "count": 2980472, "is_parallel": true, "self": 421.8497571221669 } } } } }, "steps_from_proto": { "total": 0.03901578700970276, "count": 56, "is_parallel": true, "self": 0.00824886504051392, "children": { "_process_rank_one_or_two_observation": { "total": 0.030766921969188843, "count": 224, "is_parallel": true, "self": 0.030766921969188843 } } } } } } } } }, "trainer_advance": { "total": 12681.00246206758, "count": 372560, "self": 65.80724746843407, "children": { "process_trajectory": { "total": 1194.1847808191087, "count": 372560, "self": 1193.088690232118, "children": { "RLTrainer._checkpoint": { "total": 1.0960905869906128, "count": 11, "self": 1.0960905869906128 } } }, "_update_policy": { "total": 11421.010433780037, "count": 265, "self": 551.5973732608181, "children": { "TorchPOCAOptimizer.update": { "total": 10869.413060519219, "count": 7958, "self": 10869.413060519219 } } } } } } }, "trainer_threads": { "total": 1.1609954526647925e-06, "count": 1, "self": 1.1609954526647925e-06 }, "TrainerController._save_models": { "total": 0.0924942519995966, "count": 1, "self": 0.0024630129992146976, "children": { "RLTrainer._checkpoint": { "total": 0.0900312390003819, "count": 1, "self": 0.0900312390003819 } } } } } } }