{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.6617156267166138, "min": 1.6463146209716797, "max": 3.2956645488739014, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33021.61328125, "min": 24217.63671875, "max": 149737.25, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.61538461538461, "min": 39.03252032520325, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19880.0, "min": 12264.0, "max": 31552.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1555.9673372254435, "min": 1179.1797868907395, "max": 1590.9325789863262, "count": 930 }, "SoccerTwos.Self-play.ELO.sum": { "value": 283186.05537503073, "min": 2358.359573781479, "max": 364048.51230904856, "count": 930 }, "SoccerTwos.Step.mean": { "value": 9999942.0, "min": 9794.0, "max": 9999942.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999942.0, "min": 9794.0, "max": 9999942.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.00566557701677084, "min": -0.11612775921821594, "max": 0.1739158183336258, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.025469422340393, "min": -21.817583084106445, "max": 30.623865127563477, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006585672963410616, "min": -0.12416495382785797, "max": 0.17600120604038239, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1920068264007568, "min": -22.194427490234375, "max": 31.483455657958984, "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": -0.034324860045923056, "min": -0.6153846153846154, "max": 0.5792411749853807, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.212799668312073, "min": -67.71960020065308, "max": 55.46440005302429, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.034324860045923056, "min": -0.6153846153846154, "max": 0.5792411749853807, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.212799668312073, "min": -67.71960020065308, "max": 55.46440005302429, "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": 0.01709441957840075, "min": 0.009994413168169559, "max": 0.02478652395075187, "count": 480 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01709441957840075, "min": 0.009994413168169559, "max": 0.02478652395075187, "count": 480 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10897446970144907, "min": 1.9014857267999712e-06, "max": 0.12384716247518858, "count": 480 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10897446970144907, "min": 1.9014857267999712e-06, "max": 0.12384716247518858, "count": 480 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11074638590216637, "min": 1.9274608916930448e-06, "max": 0.12620120868086815, "count": 480 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11074638590216637, "min": 1.9274608916930448e-06, "max": 0.12620120868086815, "count": 480 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 480 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 480 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 480 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 480 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 480 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 480 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675580294", "python_version": "3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) \n[GCC 11.3.0]", "command_line_arguments": "/home/ubuntu/anaconda3/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTows.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1675595889" }, "total": 15595.732323962999, "count": 1, "self": 0.6238023289988632, "children": { "run_training.setup": { "total": 0.011555836999832536, "count": 1, "self": 0.011555836999832536 }, "TrainerController.start_learning": { "total": 15595.096965797, "count": 1, "self": 11.560025735405361, "children": { "TrainerController._reset_env": { "total": 25.2714812480026, "count": 50, "self": 25.2714812480026 }, "TrainerController.advance": { "total": 15558.051513543593, "count": 681749, "self": 11.613678871721277, "children": { "env_step": { "total": 11450.49399927406, "count": 681749, "self": 8612.57805302549, "children": { "SubprocessEnvManager._take_step": { "total": 2831.1686524939378, "count": 681749, "self": 85.78754740146633, "children": { "TorchPolicy.evaluate": { "total": 2745.3811050924714, "count": 1261866, "self": 2745.3811050924714 } } }, "workers": { "total": 6.74729375463221, "count": 681749, "self": 0.0, "children": { "worker_root": { "total": 15569.345536593828, "count": 681749, "is_parallel": true, "self": 8346.1925474314, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003635031999920102, "count": 2, "is_parallel": true, "self": 0.0016677169999184116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019673150000016904, "count": 8, "is_parallel": true, "self": 0.0019673150000016904 } } }, "UnityEnvironment.step": { "total": 0.06020226600003298, "count": 1, "is_parallel": true, "self": 0.0006175999999413762, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004335640001045249, "count": 1, "is_parallel": true, "self": 0.0004335640001045249 }, "communicator.exchange": { "total": 0.02269918299998608, "count": 1, "is_parallel": true, "self": 0.02269918299998608 }, "steps_from_proto": { "total": 0.036451919000001, "count": 2, "is_parallel": true, "self": 0.0004153159998168121, "children": { "_process_rank_one_or_two_observation": { "total": 0.036036603000184186, "count": 8, "is_parallel": true, "self": 0.036036603000184186 } } } } } } }, "UnityEnvironment.step": { "total": 7223.063650097429, "count": 681748, "is_parallel": true, "self": 355.0705518904397, "children": { "UnityEnvironment._generate_step_input": { "total": 225.13519776315934, "count": 681748, "is_parallel": true, "self": 225.13519776315934 }, "communicator.exchange": { "total": 5503.697231526183, "count": 681748, "is_parallel": true, "self": 5503.697231526183 }, "steps_from_proto": { "total": 1139.1606689176472, "count": 1363496, "is_parallel": true, "self": 218.59192158999144, "children": { "_process_rank_one_or_two_observation": { "total": 920.5687473276557, "count": 5453984, "is_parallel": true, "self": 920.5687473276557 } } } } }, "steps_from_proto": { "total": 0.0893390650001038, "count": 98, "is_parallel": true, "self": 0.017216250994124493, "children": { "_process_rank_one_or_two_observation": { "total": 0.07212281400597931, "count": 392, "is_parallel": true, "self": 0.07212281400597931 } } } } } } } } }, "trainer_advance": { "total": 4095.943835397811, "count": 681749, "self": 82.51193142321517, "children": { "process_trajectory": { "total": 1604.3090973445778, "count": 681749, "self": 1599.7561460175793, "children": { "RLTrainer._checkpoint": { "total": 4.552951326998482, "count": 20, "self": 4.552951326998482 } } }, "_update_policy": { "total": 2409.122806630018, "count": 480, "self": 1424.0430153710379, "children": { "TorchPOCAOptimizer.update": { "total": 985.0797912589803, "count": 14400, "self": 985.0797912589803 } } } } } } }, "trainer_threads": { "total": 9.190007403958589e-07, "count": 1, "self": 9.190007403958589e-07 }, "TrainerController._save_models": { "total": 0.21394435099864495, "count": 1, "self": 0.0015055409967317246, "children": { "RLTrainer._checkpoint": { "total": 0.21243881000191323, "count": 1, "self": 0.21243881000191323 } } } } } } }