{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.925425410270691, "min": 1.915759801864624, "max": 3.2958054542541504, "count": 999 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37584.3046875, "min": 16128.560546875, "max": 120293.8125, "count": 999 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.34065934065934, "min": 38.62698412698413, "max": 999.0, "count": 999 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19052.0, "min": 8600.0, "max": 31840.0, "count": 999 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1529.3533261043233, "min": 1183.3205100604046, "max": 1580.9917070831711, "count": 963 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278342.30535098683, "min": 2367.107393890611, "max": 387650.7991294721, "count": 963 }, "SoccerTwos.Step.mean": { "value": 9999986.0, "min": 9936.0, "max": 9999986.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999986.0, "min": 9936.0, "max": 9999986.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00248384615406394, "min": -0.08259005099534988, "max": 0.16389651596546173, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.4520599842071533, "min": -17.674270629882812, "max": 21.08759307861328, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0029731635004281998, "min": -0.08249327540397644, "max": 0.17476192116737366, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5411157608032227, "min": -17.653560638427734, "max": 20.636287689208984, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06966813187022786, "min": -0.7774249985814095, "max": 0.592375762534864, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 12.67960000038147, "min": -55.94960010051727, "max": 51.77119994163513, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06966813187022786, "min": -0.7774249985814095, "max": 0.592375762534864, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 12.67960000038147, "min": -55.94960010051727, "max": 51.77119994163513, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017772479609023624, "min": 0.013106207802290252, "max": 0.02294513695621087, "count": 241 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017772479609023624, "min": 0.013106207802290252, "max": 0.02294513695621087, "count": 241 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10266318197051684, "min": 0.00021628589521848577, "max": 0.10266318197051684, "count": 241 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10266318197051684, "min": 0.00021628589521848577, "max": 0.10266318197051684, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10306878151992957, "min": 0.00021604419152936315, "max": 0.10306878151992957, "count": 241 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10306878151992957, "min": 0.00021604419152936315, "max": 0.10306878151992957, "count": 241 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.039799480599895e-07, "min": 1.039799480599895e-07, "max": 0.00019908356045822005, "count": 241 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 1.039799480599895e-07, "min": 1.039799480599895e-07, "max": 0.00019908356045822005, "count": 241 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10005193999999999, "min": 0.10005193999999999, "max": 0.19954178000000003, "count": 241 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10005193999999999, "min": 0.10005193999999999, "max": 0.19954178000000003, "count": 241 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.2591805999999739e-05, "min": 1.2591805999999739e-05, "max": 0.004977134822000001, "count": 241 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.2591805999999739e-05, "min": 1.2591805999999739e-05, "max": 0.004977134822000001, "count": 241 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675676285", "python_version": "3.9.15 (main, Oct 12 2022, 19:14:24) \n[GCC 9.4.0]", "command_line_arguments": "/home/alex_ch/Documents/soccer/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos11 --no-graphics --forc", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675689426" }, "total": 13141.40194816608, "count": 1, "self": 0.2199119576252997, "children": { "run_training.setup": { "total": 0.017643160186707973, "count": 1, "self": 0.017643160186707973 }, "TrainerController.start_learning": { "total": 13141.164393048268, "count": 1, "self": 11.515696075744927, "children": { "TrainerController._reset_env": { "total": 3.5481117190793157, "count": 40, "self": 3.5481117190793157 }, "TrainerController.advance": { "total": 13125.719392045401, "count": 670314, "self": 12.56607809336856, "children": { "env_step": { "total": 10137.776378094219, "count": 670314, "self": 7932.83226008201, "children": { "SubprocessEnvManager._take_step": { "total": 2197.358084292151, "count": 670314, "self": 64.50146153476089, "children": { "TorchPolicy.evaluate": { "total": 2132.85662275739, "count": 1268100, "self": 2132.85662275739 } } }, "workers": { "total": 7.586033720057458, "count": 670314, "self": 0.0, "children": { "worker_root": { "total": 13123.940445470624, "count": 670314, "is_parallel": true, "self": 6547.930196742527, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017680441960692406, "count": 2, "is_parallel": true, "self": 0.0004641655832529068, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013038786128163338, "count": 8, "is_parallel": true, "self": 0.0013038786128163338 } } }, "UnityEnvironment.step": { "total": 0.024935865309089422, "count": 1, "is_parallel": true, "self": 0.0004292144440114498, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003173109143972397, "count": 1, "is_parallel": true, "self": 0.0003173109143972397 }, "communicator.exchange": { "total": 0.022921456955373287, "count": 1, "is_parallel": true, "self": 0.022921456955373287 }, "steps_from_proto": { "total": 0.0012678829953074455, "count": 2, "is_parallel": true, "self": 0.0002644117921590805, "children": { "_process_rank_one_or_two_observation": { "total": 0.001003471203148365, "count": 8, "is_parallel": true, "self": 0.001003471203148365 } } } } } } }, "UnityEnvironment.step": { "total": 6575.949935941491, "count": 670313, "is_parallel": true, "self": 386.8673889040947, "children": { "UnityEnvironment._generate_step_input": { "total": 225.78400005586445, "count": 670313, "is_parallel": true, "self": 225.78400005586445 }, "communicator.exchange": { "total": 4956.217983013019, "count": 670313, "is_parallel": true, "self": 4956.217983013019 }, "steps_from_proto": { "total": 1007.0805639685132, "count": 1340626, "is_parallel": true, "self": 190.8026582240127, "children": { "_process_rank_one_or_two_observation": { "total": 816.2779057445005, "count": 5362504, "is_parallel": true, "self": 816.2779057445005 } } } } }, "steps_from_proto": { "total": 0.06031278660520911, "count": 78, "is_parallel": true, "self": 0.011089394800364971, "children": { "_process_rank_one_or_two_observation": { "total": 0.04922339180484414, "count": 312, "is_parallel": true, "self": 0.04922339180484414 } } } } } } } } }, "trainer_advance": { "total": 2975.376935857814, "count": 670314, "self": 83.94245607219636, "children": { "process_trajectory": { "total": 1001.9303183853626, "count": 670314, "self": 994.2248323266394, "children": { "RLTrainer._checkpoint": { "total": 7.7054860587231815, "count": 20, "self": 7.7054860587231815 } } }, "_update_policy": { "total": 1889.5041614002548, "count": 241, "self": 1125.2545917071402, "children": { "TorchPOCAOptimizer.update": { "total": 764.2495696931146, "count": 14466, "self": 764.2495696931146 } } } } } } }, "trainer_threads": { "total": 8.819624781608582e-07, "count": 1, "self": 8.819624781608582e-07 }, "TrainerController._save_models": { "total": 0.38119232608005404, "count": 1, "self": 0.00203861016780138, "children": { "RLTrainer._checkpoint": { "total": 0.37915371591225266, "count": 1, "self": 0.37915371591225266 } } } } } } }