{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9712942838668823, "min": 1.9661911725997925, "max": 3.2957358360290527, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40813.67578125, "min": 15614.361328125, "max": 105463.515625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.55555555555556, "min": 42.293103448275865, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19620.0, "min": 10788.0, "max": 30272.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1559.6469771497655, "min": 1200.7492804441454, "max": 1577.0405009914823, "count": 491 }, "SoccerTwos.Self-play.ELO.sum": { "value": 252662.810298262, "min": 2401.4985608882907, "max": 362080.720767181, "count": 491 }, "SoccerTwos.Step.mean": { "value": 4999992.0, "min": 9152.0, "max": 4999992.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999992.0, "min": 9152.0, "max": 4999992.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0013691852800548077, "min": -0.09895986318588257, "max": 0.17183257639408112, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.22317719459533691, "min": -16.72421646118164, "max": 26.218730926513672, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00021639192709699273, "min": -0.09728053957223892, "max": 0.18304979801177979, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.03527188301086426, "min": -16.440410614013672, "max": 27.166671752929688, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.014895704626305703, "min": -0.42857142857142855, "max": 0.3610380973134722, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.4279998540878296, "min": -51.80679976940155, "max": 57.0787992477417, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.014895704626305703, "min": -0.42857142857142855, "max": 0.3610380973134722, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.4279998540878296, "min": -51.80679976940155, "max": 57.0787992477417, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015365875405647482, "min": 0.0106980721452904, "max": 0.023673540592426434, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015365875405647482, "min": 0.0106980721452904, "max": 0.023673540592426434, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09721296106775602, "min": 0.0001224813905234138, "max": 0.11625648538271587, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09721296106775602, "min": 0.0001224813905234138, "max": 0.11625648538271587, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09830297008156777, "min": 0.00012409707390664455, "max": 0.11816722899675369, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09830297008156777, "min": 0.00012409707390664455, "max": 0.11816722899675369, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719005436", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/georgy/miniconda3/envs/hf-rl-course/bin/mlagents-learn ./configs/SoccerTwos.yaml --env=../ml-agents/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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719012450" }, "total": 7013.90845661913, "count": 1, "self": 0.2687763930298388, "children": { "run_training.setup": { "total": 0.014317912980914116, "count": 1, "self": 0.014317912980914116 }, "TrainerController.start_learning": { "total": 7013.62536231312, "count": 1, "self": 5.0036841097753495, "children": { "TrainerController._reset_env": { "total": 1.7660642263945192, "count": 25, "self": 1.7660642263945192 }, "TrainerController.advance": { "total": 7006.711907642661, "count": 339089, "self": 4.354088980238885, "children": { "env_step": { "total": 5576.542560391128, "count": 339089, "self": 4388.083748762729, "children": { "SubprocessEnvManager._take_step": { "total": 1185.1619284837507, "count": 339089, "self": 27.26024706894532, "children": { "TorchPolicy.evaluate": { "total": 1157.9016814148054, "count": 630752, "self": 1157.9016814148054 } } }, "workers": { "total": 3.2968831446487457, "count": 339089, "self": 0.0, "children": { "worker_root": { "total": 7005.051289109746, "count": 339089, "is_parallel": true, "self": 3254.795083300909, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003715916071087122, "count": 2, "is_parallel": true, "self": 0.0007357143331319094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0029802017379552126, "count": 8, "is_parallel": true, "self": 0.0029802017379552126 } } }, "UnityEnvironment.step": { "total": 0.02689134795218706, "count": 1, "is_parallel": true, "self": 0.0008379898499697447, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006968711968511343, "count": 1, "is_parallel": true, "self": 0.0006968711968511343 }, "communicator.exchange": { "total": 0.022590431850403547, "count": 1, "is_parallel": true, "self": 0.022590431850403547 }, "steps_from_proto": { "total": 0.002766055054962635, "count": 2, "is_parallel": true, "self": 0.0004009511321783066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023651039227843285, "count": 8, "is_parallel": true, "self": 0.0023651039227843285 } } } } } } }, "UnityEnvironment.step": { "total": 3750.204459583154, "count": 339088, "is_parallel": true, "self": 238.5870046846103, "children": { "UnityEnvironment._generate_step_input": { "total": 156.512111854041, "count": 339088, "is_parallel": true, "self": 156.512111854041 }, "communicator.exchange": { "total": 2673.0863169804215, "count": 339088, "is_parallel": true, "self": 2673.0863169804215 }, "steps_from_proto": { "total": 682.0190260640811, "count": 678176, "is_parallel": true, "self": 108.02852755994536, "children": { "_process_rank_one_or_two_observation": { "total": 573.9904985041358, "count": 2712704, "is_parallel": true, "self": 573.9904985041358 } } } } }, "steps_from_proto": { "total": 0.051746225683018565, "count": 48, "is_parallel": true, "self": 0.008203333243727684, "children": { "_process_rank_one_or_two_observation": { "total": 0.04354289243929088, "count": 192, "is_parallel": true, "self": 0.04354289243929088 } } } } } } } } }, "trainer_advance": { "total": 1425.8152582712937, "count": 339089, "self": 44.6332890947815, "children": { "process_trajectory": { "total": 566.3861913965084, "count": 339089, "self": 565.0334996974561, "children": { "RLTrainer._checkpoint": { "total": 1.3526916990522295, "count": 10, "self": 1.3526916990522295 } } }, "_update_policy": { "total": 814.7957777800038, "count": 240, "self": 509.6999193832744, "children": { "TorchPOCAOptimizer.update": { "total": 305.09585839672945, "count": 7203, "self": 305.09585839672945 } } } } } } }, "trainer_threads": { "total": 5.711335688829422e-07, "count": 1, "self": 5.711335688829422e-07 }, "TrainerController._save_models": { "total": 0.14370576315559447, "count": 1, "self": 0.0014321389608085155, "children": { "RLTrainer._checkpoint": { "total": 0.14227362419478595, "count": 1, "self": 0.14227362419478595 } } } } } } }