{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.479911208152771, "min": 1.3237388134002686, "max": 3.295701265335083, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29977.08203125, "min": 12411.583984375, "max": 122450.265625, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 78.34920634920636, "min": 39.62096774193548, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19744.0, "min": 11096.0, "max": 30160.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1846.5684583727525, "min": 1199.3956180289204, "max": 1865.6424935075586, "count": 4937 }, "SoccerTwos.Self-play.ELO.sum": { "value": 232667.6257549668, "min": 2399.5958250738668, "max": 401305.17193841, "count": 4937 }, "SoccerTwos.Step.mean": { "value": 49999862.0, "min": 9096.0, "max": 49999862.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999862.0, "min": 9096.0, "max": 49999862.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014512530528008938, "min": -0.13971209526062012, "max": 0.14427369832992554, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.8285788297653198, "min": -25.846736907958984, "max": 19.056289672851562, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.014197468757629395, "min": -0.13814572989940643, "max": 0.14304670691490173, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.7888810634613037, "min": -25.556961059570312, "max": 19.17021942138672, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05351111103617956, "min": -0.75, "max": 0.3675822205013699, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.742399990558624, "min": -56.312200129032135, "max": 56.91820031404495, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05351111103617956, "min": -0.75, "max": 0.3675822205013699, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.742399990558624, "min": -56.312200129032135, "max": 56.91820031404495, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015061931361560709, "min": 0.009686602939715764, "max": 0.025481848779600115, "count": 2419 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015061931361560709, "min": 0.009686602939715764, "max": 0.025481848779600115, "count": 2419 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09468170826633772, "min": 8.975703084483181e-07, "max": 0.13113947436213494, "count": 2419 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09468170826633772, "min": 8.975703084483181e-07, "max": 0.13113947436213494, "count": 2419 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09514425372083982, "min": 9.11561358899841e-07, "max": 0.13482531333963077, "count": 2419 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09514425372083982, "min": 9.11561358899841e-07, "max": 0.13482531333963077, "count": 2419 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2419 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2419 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2419 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2419 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2419 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2419 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1741991909", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --force --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742112723" }, "total": 120814.14986484099, "count": 1, "self": 0.32583349298511166, "children": { "run_training.setup": { "total": 0.029320462999748997, "count": 1, "self": 0.029320462999748997 }, "TrainerController.start_learning": { "total": 120813.794710885, "count": 1, "self": 82.64801434721448, "children": { "TrainerController._reset_env": { "total": 11.042979621996892, "count": 250, "self": 11.042979621996892 }, "TrainerController.advance": { "total": 120719.8470295598, "count": 3429312, "self": 80.55465696916508, "children": { "env_step": { "total": 95364.23530131021, "count": 3429312, "self": 71898.50496000025, "children": { "SubprocessEnvManager._take_step": { "total": 23411.061995684562, "count": 3429312, "self": 676.4203516209127, "children": { "TorchPolicy.evaluate": { "total": 22734.64164406365, "count": 6291290, "self": 22734.64164406365 } } }, "workers": { "total": 54.66834562540225, "count": 3429312, "self": 0.0, "children": { "worker_root": { "total": 120658.3198810897, "count": 3429312, "is_parallel": true, "self": 59316.00655987379, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035691040011442965, "count": 2, "is_parallel": true, "self": 0.0009568930026944145, "children": { "_process_rank_one_or_two_observation": { "total": 0.002612210998449882, "count": 8, "is_parallel": true, "self": 0.002612210998449882 } } }, "UnityEnvironment.step": { "total": 0.030402770999899076, "count": 1, "is_parallel": true, "self": 0.0014687459997730912, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0010806159998537623, "count": 1, "is_parallel": true, "self": 0.0010806159998537623 }, "communicator.exchange": { "total": 0.023824339999919175, "count": 1, "is_parallel": true, "self": 0.023824339999919175 }, "steps_from_proto": { "total": 0.004029069000353047, "count": 2, "is_parallel": true, "self": 0.0007847000006222515, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032443689997307956, "count": 8, "is_parallel": true, "self": 0.0032443689997307956 } } } } } } }, "UnityEnvironment.step": { "total": 61341.28248714986, "count": 3429311, "is_parallel": true, "self": 4200.732071779654, "children": { "UnityEnvironment._generate_step_input": { "total": 2801.8117705018594, "count": 3429311, "is_parallel": true, "self": 2801.8117705018594 }, "communicator.exchange": { "total": 43539.453649200754, "count": 3429311, "is_parallel": true, "self": 43539.453649200754 }, "steps_from_proto": { "total": 10799.284995667596, "count": 6858622, "is_parallel": true, "self": 2007.38323475351, "children": { "_process_rank_one_or_two_observation": { "total": 8791.901760914086, "count": 27434488, "is_parallel": true, "self": 8791.901760914086 } } } } }, "steps_from_proto": { "total": 1.0308340660467366, "count": 498, "is_parallel": true, "self": 0.18941235806323675, "children": { "_process_rank_one_or_two_observation": { "total": 0.8414217079834998, "count": 1992, "is_parallel": true, "self": 0.8414217079834998 } } } } } } } } }, "trainer_advance": { "total": 25275.057071280415, "count": 3429312, "self": 642.4818696860239, "children": { "process_trajectory": { "total": 12246.831997823145, "count": 3429312, "self": 12220.272090646127, "children": { "RLTrainer._checkpoint": { "total": 26.55990717701752, "count": 100, "self": 26.55990717701752 } } }, "_update_policy": { "total": 12385.743203771246, "count": 2419, "self": 6473.206506693914, "children": { "TorchPOCAOptimizer.update": { "total": 5912.536697077332, "count": 72576, "self": 5912.536697077332 } } } } } } }, "trainer_threads": { "total": 9.920040611177683e-07, "count": 1, "self": 9.920040611177683e-07 }, "TrainerController._save_models": { "total": 0.2566863639949588, "count": 1, "self": 0.0024828159948810935, "children": { "RLTrainer._checkpoint": { "total": 0.2542035480000777, "count": 1, "self": 0.2542035480000777 } } } } } } }