{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2132580280303955, "min": 3.1846652030944824, "max": 3.295759439468384, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 98916.9375, "min": 27097.08203125, "max": 106529.15625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 609.2222222222222, "min": 398.0833333333333, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21932.0, "min": 15388.0, "max": 26548.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.1489636234078, "min": 1195.483219591219, "max": 1202.9786096555342, "count": 44 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14401.787563480893, "min": 2396.1104985479037, "max": 14401.787563480893, "count": 44 }, "SoccerTwos.Step.mean": { "value": 499160.0, "min": 9290.0, "max": 499160.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499160.0, "min": 9290.0, "max": 499160.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01424437016248703, "min": -0.027376150712370872, "max": 0.014726834371685982, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.2421542853116989, "min": -0.3461591601371765, "max": 0.1914488524198532, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.016242891550064087, "min": -0.02736443467438221, "max": 0.014573918655514717, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2761291563510895, "min": -0.3770729601383209, "max": 0.18946094810962677, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3514117633595186, "min": -0.3514117633595186, "max": 0.2477538402263935, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.973999977111816, "min": -5.973999977111816, "max": 3.2207999229431152, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3514117633595186, "min": -0.3514117633595186, "max": 0.2477538402263935, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.973999977111816, "min": -5.973999977111816, "max": 3.2207999229431152, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017714444474161914, "min": 0.01238880962288628, "max": 0.02108428073115647, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017714444474161914, "min": 0.01238880962288628, "max": 0.02108428073115647, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.003472739547335853, "min": 0.00013744384693078853, "max": 0.005440379741291205, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.003472739547335853, "min": 0.00013744384693078853, "max": 0.005440379741291205, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0034728740574792027, "min": 0.00013916020858838844, "max": 0.00547612120086948, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0034728740574792027, "min": 0.00013916020858838844, "max": 0.00547612120086948, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724683307", "python_version": "3.9.18 (main, Sep 11 2023, 13:30:38) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\maava\\anaconda3\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2+cu121", "numpy_version": "1.21.2", "end_time_seconds": "1724684544" }, "total": 1237.0312437, "count": 1, "self": 0.43861839999999575, "children": { "run_training.setup": { "total": 0.2418042000000007, "count": 1, "self": 0.2418042000000007 }, "TrainerController.start_learning": { "total": 1236.3508211, "count": 1, "self": 0.6279196999914802, "children": { "TrainerController._reset_env": { "total": 11.140108799999995, "count": 3, "self": 11.140108799999995 }, "TrainerController.advance": { "total": 1224.4701394000085, "count": 33204, "self": 0.6556736999964414, "children": { "env_step": { "total": 516.7168198000111, "count": 33204, "self": 397.07340210001126, "children": { "SubprocessEnvManager._take_step": { "total": 119.20660319999807, "count": 33204, "self": 3.699288399981839, "children": { "TorchPolicy.evaluate": { "total": 115.50731480001623, "count": 65942, "self": 115.50731480001623 } } }, "workers": { "total": 0.4368145000017556, "count": 33204, "self": 0.0, "children": { "worker_root": { "total": 1225.6032269000032, "count": 33204, "is_parallel": true, "self": 912.5289798000135, "children": { "steps_from_proto": { "total": 0.007710600000004675, "count": 6, "is_parallel": true, "self": 0.001754900000355164, "children": { "_process_rank_one_or_two_observation": { "total": 0.005955699999649511, "count": 24, "is_parallel": true, "self": 0.005955699999649511 } } }, "UnityEnvironment.step": { "total": 313.06653649998964, "count": 33204, "is_parallel": true, "self": 17.22868409995766, "children": { "UnityEnvironment._generate_step_input": { "total": 11.931016199995167, "count": 33204, "is_parallel": true, "self": 11.931016199995167 }, "communicator.exchange": { "total": 231.26034250000575, "count": 33204, "is_parallel": true, "self": 231.26034250000575 }, "steps_from_proto": { "total": 52.64649370003109, "count": 66408, "is_parallel": true, "self": 10.335666100007877, "children": { "_process_rank_one_or_two_observation": { "total": 42.31082760002321, "count": 265632, "is_parallel": true, "self": 42.31082760002321 } } } } } } } } } } }, "trainer_advance": { "total": 707.097645900001, "count": 33204, "self": 4.561514999991346, "children": { "process_trajectory": { "total": 85.44851780001024, "count": 33204, "self": 85.26192190001031, "children": { "RLTrainer._checkpoint": { "total": 0.18659589999992932, "count": 1, "self": 0.18659589999992932 } } }, "_update_policy": { "total": 617.0876130999994, "count": 23, "self": 74.83724779999523, "children": { "TorchPOCAOptimizer.update": { "total": 542.2503653000042, "count": 690, "self": 542.2503653000042 } } } } } } }, "TrainerController._save_models": { "total": 0.11265320000006795, "count": 1, "self": 3.219999985049071e-05, "children": { "RLTrainer._checkpoint": { "total": 0.11262100000021746, "count": 1, "self": 0.11262100000021746 } } } } } } }