{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.609711766242981, "min": 1.5449258089065552, "max": 3.2957260608673096, "count": 2250 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30906.46484375, "min": 16196.94140625, "max": 146240.546875, "count": 2250 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.41935483870968, "min": 40.705882352941174, "max": 999.0, "count": 2250 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19500.0, "min": 15344.0, "max": 25844.0, "count": 2250 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1631.834360513127, "min": 1179.7631952700578, "max": 1668.4021746415497, "count": 1657 }, "SoccerTwos.Self-play.ELO.sum": { "value": 303521.1910554416, "min": 2363.0045066216217, "max": 391130.68000467966, "count": 1657 }, "SoccerTwos.Step.mean": { "value": 22499943.0, "min": 9940.0, "max": 22499943.0, "count": 2250 }, "SoccerTwos.Step.sum": { "value": 22499943.0, "min": 9940.0, "max": 22499943.0, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02783402055501938, "min": -0.15758347511291504, "max": 0.20508311688899994, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.204961776733398, "min": -20.4935359954834, "max": 27.915775299072266, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.027563221752643585, "min": -0.15951979160308838, "max": 0.20716986060142517, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.154322624206543, "min": -20.627216339111328, "max": 27.823421478271484, "count": 2250 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2250 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.02693155136975375, "min": -0.5833333333333334, "max": 0.4575333280695809, "count": 2250 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.036200106143951, "min": -57.246400237083435, "max": 53.058799743652344, "count": 2250 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.02693155136975375, "min": -0.5833333333333334, "max": 0.4575333280695809, "count": 2250 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.036200106143951, "min": -57.246400237083435, "max": 53.058799743652344, "count": 2250 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2250 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2250 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01755287745812287, "min": 0.010135007119364067, "max": 0.025005417516998325, "count": 1070 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01755287745812287, "min": 0.010135007119364067, "max": 0.025005417516998325, "count": 1070 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09899942129850388, "min": 5.795050791087183e-10, "max": 0.11965364292263984, "count": 1070 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09899942129850388, "min": 5.795050791087183e-10, "max": 0.11965364292263984, "count": 1070 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09978213210900624, "min": 6.815150629021124e-10, "max": 0.12178009773294131, "count": 1070 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09978213210900624, "min": 6.815150629021124e-10, "max": 0.12178009773294131, "count": 1070 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1070 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1070 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1070 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1070 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1070 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1070 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716639250", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\GLC\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716832613" }, "total": 193363.65435670002, "count": 1, "self": 10.792292800033465, "children": { "run_training.setup": { "total": 0.43808110000099987, "count": 1, "self": 0.43808110000099987 }, "TrainerController.start_learning": { "total": 193352.42398279998, "count": 1, "self": 95.62078901167843, "children": { "TrainerController._reset_env": { "total": 71.31561610018252, "count": 113, "self": 71.31561610018252 }, "TrainerController.advance": { "total": 193182.4588773881, "count": 1512610, "self": 100.93002877553226, "children": { "env_step": { "total": 67817.1227031856, "count": 1512610, "self": 49476.67221164971, "children": { "SubprocessEnvManager._take_step": { "total": 18285.465775338613, "count": 1512610, "self": 628.7786048448761, "children": { "TorchPolicy.evaluate": { "total": 17656.687170493737, "count": 2861170, "self": 17656.687170493737 } } }, "workers": { "total": 54.984716197272064, "count": 1512609, "self": 0.0, "children": { "worker_root": { "total": 193201.27350063866, "count": 1512609, "is_parallel": true, "self": 155413.50229072903, "children": { "steps_from_proto": { "total": 0.616233600419946, "count": 226, "is_parallel": true, "self": 0.12447450065519661, "children": { "_process_rank_one_or_two_observation": { "total": 0.4917590997647494, "count": 904, "is_parallel": true, "self": 0.4917590997647494 } } }, "UnityEnvironment.step": { "total": 37787.15497630922, "count": 1512609, "is_parallel": true, "self": 2041.1823491639516, "children": { "UnityEnvironment._generate_step_input": { "total": 1811.875654306321, "count": 1512609, "is_parallel": true, "self": 1811.875654306321 }, "communicator.exchange": { "total": 26907.95783263317, "count": 1512609, "is_parallel": true, "self": 26907.95783263317 }, "steps_from_proto": { "total": 7026.139140205778, "count": 3025218, "is_parallel": true, "self": 1423.2729393191403, "children": { "_process_rank_one_or_two_observation": { "total": 5602.866200886638, "count": 12100872, "is_parallel": true, "self": 5602.866200886638 } } } } } } } } } } }, "trainer_advance": { "total": 125264.40614542697, "count": 1512609, "self": 707.4680315357982, "children": { "process_trajectory": { "total": 20423.767226992524, "count": 1512609, "self": 19998.030270592484, "children": { "RLTrainer._checkpoint": { "total": 425.73695640004007, "count": 45, "self": 425.73695640004007 } } }, "_update_policy": { "total": 104133.17088689865, "count": 1070, "self": 10494.982810904243, "children": { "TorchPOCAOptimizer.update": { "total": 93638.1880759944, "count": 32100, "self": 93638.1880759944 } } } } } } }, "trainer_threads": { "total": 3.300025127828121e-06, "count": 1, "self": 3.300025127828121e-06 }, "TrainerController._save_models": { "total": 3.028697000001557, "count": 1, "self": 1.8835300000500865, "children": { "RLTrainer._checkpoint": { "total": 1.1451669999514706, "count": 1, "self": 1.1451669999514706 } } } } } } }