{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.694275140762329, "min": 1.6514707803726196, "max": 3.2957615852355957, "count": 612 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35024.0546875, "min": 22101.92578125, "max": 125759.7265625, "count": 612 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.51, "min": 43.666666666666664, "max": 999.0, "count": 612 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20204.0, "min": 16236.0, "max": 24964.0, "count": 612 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1680.6541918624032, "min": 1196.8286436159, "max": 1703.176681790927, "count": 592 }, "SoccerTwos.Self-play.ELO.sum": { "value": 336130.83837248065, "min": 2400.670570872331, "max": 361419.61620117305, "count": 592 }, "SoccerTwos.Step.mean": { "value": 6119994.0, "min": 9498.0, "max": 6119994.0, "count": 612 }, "SoccerTwos.Step.sum": { "value": 6119994.0, "min": 9498.0, "max": 6119994.0, "count": 612 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.020087381824851036, "min": -0.0951186865568161, "max": 0.18743562698364258, "count": 612 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.9973888397216797, "min": -18.611299514770508, "max": 32.988670349121094, "count": 612 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.022601088508963585, "min": -0.0991855189204216, "max": 0.18446926772594452, "count": 612 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.497616767883301, "min": -19.44036102294922, "max": 32.466590881347656, "count": 612 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 612 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 612 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.19691055324209394, "min": -0.5822285711765289, "max": 0.4100340950218114, "count": 612 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -39.1852000951767, "min": -67.867999792099, "max": 72.1660007238388, "count": 612 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19691055324209394, "min": -0.5822285711765289, "max": 0.4100340950218114, "count": 612 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -39.1852000951767, "min": -67.867999792099, "max": 72.1660007238388, "count": 612 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 612 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 612 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018075651960680263, "min": 0.009404861269285903, "max": 0.024723038620625932, "count": 293 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018075651960680263, "min": 0.009404861269285903, "max": 0.024723038620625932, "count": 293 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11116881494720778, "min": 3.985007430552893e-05, "max": 0.12105266253153484, "count": 293 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11116881494720778, "min": 3.985007430552893e-05, "max": 0.12105266253153484, "count": 293 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11312747399012248, "min": 3.145316174292627e-05, "max": 0.1233666772643725, "count": 293 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11312747399012248, "min": 3.145316174292627e-05, "max": 0.1233666772643725, "count": 293 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 293 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 293 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 293 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 293 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 293 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 293 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678116444", "python_version": "3.9.16 (main, Mar 1 2023, 18:30:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\house\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./ml-agents/mlagents/training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "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": "1678137475" }, "total": 21030.2778889, "count": 1, "self": 0.2408370000011928, "children": { "run_training.setup": { "total": 0.1250806, "count": 1, "self": 0.1250806 }, "TrainerController.start_learning": { "total": 21029.9119713, "count": 1, "self": 10.040809900354361, "children": { "TrainerController._reset_env": { "total": 7.817688400001239, "count": 31, "self": 7.817688400001239 }, "TrainerController.advance": { "total": 21011.903763499642, "count": 415049, "self": 10.23915749981461, "children": { "env_step": { "total": 7283.2836391005085, "count": 415049, "self": 5581.419482802006, "children": { "SubprocessEnvManager._take_step": { "total": 1695.5341048986973, "count": 415049, "self": 60.16887019903493, "children": { "TorchPolicy.evaluate": { "total": 1635.3652346996623, "count": 775931, "self": 1635.3652346996623 } } }, "workers": { "total": 6.330051399805274, "count": 415048, "self": 0.0, "children": { "worker_root": { "total": 21008.700451899396, "count": 415048, "is_parallel": true, "self": 16559.61056669947, "children": { "steps_from_proto": { "total": 0.05942590000402159, "count": 62, "is_parallel": true, "self": 0.012826999990548593, "children": { "_process_rank_one_or_two_observation": { "total": 0.046598900013473, "count": 248, "is_parallel": true, "self": 0.046598900013473 } } }, "UnityEnvironment.step": { "total": 4449.030459299924, "count": 415048, "is_parallel": true, "self": 225.32489310093115, "children": { "UnityEnvironment._generate_step_input": { "total": 179.56339269904132, "count": 415048, "is_parallel": true, "self": 179.56339269904132 }, "communicator.exchange": { "total": 3327.15446159991, "count": 415048, "is_parallel": true, "self": 3327.15446159991 }, "steps_from_proto": { "total": 716.9877119000416, "count": 830096, "is_parallel": true, "self": 154.99606210134925, "children": { "_process_rank_one_or_two_observation": { "total": 561.9916497986924, "count": 3320384, "is_parallel": true, "self": 561.9916497986924 } } } } } } } } } } }, "trainer_advance": { "total": 13718.38096689932, "count": 415048, "self": 70.19204039957367, "children": { "process_trajectory": { "total": 1892.5478608997626, "count": 415048, "self": 1890.7863625997632, "children": { "RLTrainer._checkpoint": { "total": 1.7614982999994027, "count": 12, "self": 1.7614982999994027 } } }, "_update_policy": { "total": 11755.641065599984, "count": 293, "self": 1069.7929925998633, "children": { "TorchPOCAOptimizer.update": { "total": 10685.848073000121, "count": 8790, "self": 10685.848073000121 } } } } } } }, "trainer_threads": { "total": 2.1000014385208488e-06, "count": 1, "self": 2.1000014385208488e-06 }, "TrainerController._save_models": { "total": 0.14970739999989746, "count": 1, "self": 0.0066014000003633555, "children": { "RLTrainer._checkpoint": { "total": 0.1431059999995341, "count": 1, "self": 0.1431059999995341 } } } } } } }