{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7722052335739136, "min": 0.7508076429367065, "max": 3.2957513332366943, "count": 3103 }, "SoccerTwos.Policy.Entropy.sum": { "value": 20040.26953125, "min": 421.8561706542969, "max": 300887.625, "count": 3103 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.50588235294118, "min": 39.21774193548387, "max": 999.0, "count": 3103 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19892.0, "min": 7992.0, "max": 38800.0, "count": 3103 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1655.4551733286996, "min": 1194.1831918904513, "max": 1726.8866978130923, "count": 3091 }, "SoccerTwos.Self-play.ELO.sum": { "value": 281427.37946587894, "min": 2392.139449323783, "max": 397688.18605291774, "count": 3091 }, "SoccerTwos.Step.mean": { "value": 31029995.0, "min": 9816.0, "max": 31029995.0, "count": 3103 }, "SoccerTwos.Step.sum": { "value": 31029995.0, "min": 9816.0, "max": 31029995.0, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.012561212293803692, "min": -0.10789082944393158, "max": 0.14437440037727356, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.135406017303467, "min": -21.25676918029785, "max": 20.037342071533203, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009676625020802021, "min": -0.10898121446371078, "max": 0.14241483807563782, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.6450262069702148, "min": -21.707752227783203, "max": 19.850662231445312, "count": 3103 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3103 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04213176544974832, "min": -0.4895749995484948, "max": 0.5014400005340576, "count": 3103 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.162400126457214, "min": -69.17599999904633, "max": 64.46680080890656, "count": 3103 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04213176544974832, "min": -0.4895749995484948, "max": 0.5014400005340576, "count": 3103 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.162400126457214, "min": -69.17599999904633, "max": 64.46680080890656, "count": 3103 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3103 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3103 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01780883798146533, "min": 0.012434850020023683, "max": 0.024863777283462694, "count": 754 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01780883798146533, "min": 0.012434850020023683, "max": 0.024863777283462694, "count": 754 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09168587923049927, "min": 0.0013380789212533272, "max": 0.1214194405823946, "count": 754 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09168587923049927, "min": 0.0013380789212533272, "max": 0.1214194405823946, "count": 754 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09295500939091046, "min": 0.0013492340386922783, "max": 0.1252348172167937, "count": 754 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09295500939091046, "min": 0.0013492340386922783, "max": 0.1252348172167937, "count": 754 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 6.754008248666498e-05, "min": 6.754008248666498e-05, "max": 0.00029968566010478003, "count": 754 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 6.754008248666498e-05, "min": 6.754008248666498e-05, "max": 0.00029968566010478003, "count": 754 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.13377000250000004, "min": 0.13377000250000004, "max": 0.24984283000000002, "count": 754 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.13377000250000004, "min": 0.13377000250000004, "max": 0.24984283000000002, "count": 754 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0011334154165, "min": 0.0011334154165, "max": 0.004994771477999998, "count": 754 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0011334154165, "min": 0.0011334154165, "max": 0.004994771477999998, "count": 754 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675896938", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Keano2 --no-graphics --num-envs=3", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675951938" }, "total": 55000.792964600005, "count": 1, "self": 0.5562214000019594, "children": { "run_training.setup": { "total": 0.18205910000000003, "count": 1, "self": 0.18205910000000003 }, "TrainerController.start_learning": { "total": 55000.0546841, "count": 1, "self": 44.47707250079111, "children": { "TrainerController._reset_env": { "total": 8.62760900004237, "count": 156, "self": 8.62760900004237 }, "TrainerController.advance": { "total": 54946.81010599917, "count": 1921362, "self": 38.6051973021531, "children": { "env_step": { "total": 12445.740336898823, "count": 1921362, "self": 4190.723605199239, "children": { "SubprocessEnvManager._take_step": { "total": 8232.318773904692, "count": 2166682, "self": 261.4100139086968, "children": { "TorchPolicy.evaluate": { "total": 7970.908759995995, "count": 3944166, "self": 7970.908759995995 } } }, "workers": { "total": 22.697957794893757, "count": 1921362, "self": 0.0, "children": { "worker_root": { "total": 164782.59743910583, "count": 2166473, "is_parallel": true, "self": 144693.15303580926, "children": { "steps_from_proto": { "total": 0.6477376999521338, "count": 936, "is_parallel": true, "self": 0.13200409975825123, "children": { "_process_rank_one_or_two_observation": { "total": 0.5157336001938826, "count": 3744, "is_parallel": true, "self": 0.5157336001938826 } } }, "UnityEnvironment.step": { "total": 20088.79666559662, "count": 2166473, "is_parallel": true, "self": 1055.1520245860447, "children": { "UnityEnvironment._generate_step_input": { "total": 855.6345047999873, "count": 2166473, "is_parallel": true, "self": 855.6345047999873 }, "communicator.exchange": { "total": 15023.869842703287, "count": 2166473, "is_parallel": true, "self": 15023.869842703287 }, "steps_from_proto": { "total": 3154.140293507301, "count": 4332946, "is_parallel": true, "self": 643.5659081962363, "children": { "_process_rank_one_or_two_observation": { "total": 2510.574385311065, "count": 17331784, "is_parallel": true, "self": 2510.574385311065 } } } } } } } } } } }, "trainer_advance": { "total": 42462.46457179819, "count": 1921362, "self": 347.17189329535904, "children": { "process_trajectory": { "total": 7602.200574202841, "count": 1921362, "self": 7591.637804902831, "children": { "RLTrainer._checkpoint": { "total": 10.562769300010586, "count": 62, "self": 10.562769300010586 } } }, "_update_policy": { "total": 34513.09210429999, "count": 755, "self": 4113.9223459994755, "children": { "TorchPOCAOptimizer.update": { "total": 30399.169758300515, "count": 45303, "self": 30399.169758300515 } } } } } } }, "trainer_threads": { "total": 1.1000010999850929e-06, "count": 1, "self": 1.1000010999850929e-06 }, "TrainerController._save_models": { "total": 0.1398955000040587, "count": 1, "self": 0.008740500001295004, "children": { "RLTrainer._checkpoint": { "total": 0.1311550000027637, "count": 1, "self": 0.1311550000027637 } } } } } } }