{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5281283855438232, "min": 1.51893949508667, "max": 3.295815944671631, "count": 1518 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31198.26953125, "min": 14103.87109375, "max": 130326.140625, "count": 1518 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.35526315789474, "min": 43.846846846846844, "max": 999.0, "count": 1518 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19260.0, "min": 14112.0, "max": 26076.0, "count": 1518 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1684.6709307184121, "min": 1178.148824031623, "max": 1684.6709307184121, "count": 1451 }, "SoccerTwos.Self-play.ELO.sum": { "value": 256069.98146919865, "min": 2356.297648063246, "max": 345320.29804062785, "count": 1451 }, "SoccerTwos.Step.mean": { "value": 15179987.0, "min": 9054.0, "max": 15179987.0, "count": 1518 }, "SoccerTwos.Step.sum": { "value": 15179987.0, "min": 9054.0, "max": 15179987.0, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.026739638298749924, "min": -0.1436135172843933, "max": 0.2555159032344818, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.091164588928223, "min": -23.983457565307617, "max": 30.277732849121094, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.02780262380838394, "min": -0.15162380039691925, "max": 0.2591020464897156, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.253801345825195, "min": -25.32117462158203, "max": 27.891921997070312, "count": 1518 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1518 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.10177124481575162, "min": -0.7142857142857143, "max": 0.6802690971981395, "count": 1518 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.571000456809998, "min": -61.30559992790222, "max": 61.87840008735657, "count": 1518 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.10177124481575162, "min": -0.7142857142857143, "max": 0.6802690971981395, "count": 1518 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.571000456809998, "min": -61.30559992790222, "max": 61.87840008735657, "count": 1518 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1518 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1518 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022751482788589784, "min": 0.01206635746639222, "max": 0.028181853886053432, "count": 730 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022751482788589784, "min": 0.01206635746639222, "max": 0.028181853886053432, "count": 730 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09225530885159969, "min": 1.3613655616140364e-07, "max": 0.12491751350462436, "count": 730 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09225530885159969, "min": 1.3613655616140364e-07, "max": 0.12491751350462436, "count": 730 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09491726122796536, "min": 1.362520134939871e-07, "max": 0.13019061665982007, "count": 730 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09491726122796536, "min": 1.362520134939871e-07, "max": 0.13019061665982007, "count": 730 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.00027864246233939204, "min": 0.00027864246233939204, "max": 0.00039979000005250007, "count": 730 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.00027864246233939204, "min": 0.00027864246233939204, "max": 0.00039979000005250007, "count": 730 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.169660608, "min": 0.169660608, "max": 0.19994749999999997, "count": 730 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.169660608, "min": 0.169660608, "max": 0.19994749999999997, "count": 730 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0034860643392000006, "min": 0.0034860643392000006, "max": 0.00499738025, "count": 730 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0034860643392000006, "min": 0.0034860643392000006, "max": 0.00499738025, "count": 730 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701964854", "python_version": "3.10.1 (tags/v3.10.1:2cd268a, Dec 6 2021, 19:10:37) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\D:\\backup\\PycharmProjects\\ml-agents\\venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1702027803" }, "total": 62948.622758000005, "count": 1, "self": 0.819124700006796, "children": { "run_training.setup": { "total": 0.11583329999848502, "count": 1, "self": 0.11583329999848502 }, "TrainerController.start_learning": { "total": 62947.6878, "count": 1, "self": 23.613129600860702, "children": { "TrainerController._reset_env": { "total": 6.999240200027998, "count": 76, "self": 6.999240200027998 }, "TrainerController.advance": { "total": 62914.08007509912, "count": 1028470, "self": 23.77957069518743, "children": { "env_step": { "total": 17688.274200101354, "count": 1028470, "self": 13484.518638708934, "children": { "SubprocessEnvManager._take_step": { "total": 4189.176620897037, "count": 1028470, "self": 126.30452050052918, "children": { "TorchPolicy.evaluate": { "total": 4062.8721003965074, "count": 1916096, "self": 4062.8721003965074 } } }, "workers": { "total": 14.578940495382994, "count": 1028469, "self": 0.0, "children": { "worker_root": { "total": 62905.74303450515, "count": 1028469, "is_parallel": true, "self": 51959.60016410397, "children": { "steps_from_proto": { "total": 0.12947239996356075, "count": 152, "is_parallel": true, "self": 0.025777700015169103, "children": { "_process_rank_one_or_two_observation": { "total": 0.10369469994839164, "count": 608, "is_parallel": true, "self": 0.10369469994839164 } } }, "UnityEnvironment.step": { "total": 10946.013398001214, "count": 1028469, "is_parallel": true, "self": 529.7143207028057, "children": { "UnityEnvironment._generate_step_input": { "total": 417.8714918990627, "count": 1028469, "is_parallel": true, "self": 417.8714918990627 }, "communicator.exchange": { "total": 8264.872950007, "count": 1028469, "is_parallel": true, "self": 8264.872950007 }, "steps_from_proto": { "total": 1733.5546353923455, "count": 2056938, "is_parallel": true, "self": 346.06766029520077, "children": { "_process_rank_one_or_two_observation": { "total": 1387.4869750971448, "count": 8227752, "is_parallel": true, "self": 1387.4869750971448 } } } } } } } } } } }, "trainer_advance": { "total": 45202.02630430258, "count": 1028469, "self": 177.75935199018568, "children": { "process_trajectory": { "total": 4369.7174340123565, "count": 1028469, "self": 4298.999762812375, "children": { "RLTrainer._checkpoint": { "total": 70.71767119998185, "count": 30, "self": 70.71767119998185 } } }, "_update_policy": { "total": 40654.54951830003, "count": 730, "self": 2319.1410130987933, "children": { "TorchPOCAOptimizer.update": { "total": 38335.40850520124, "count": 29208, "self": 38335.40850520124 } } } } } } }, "trainer_threads": { "total": 1.2999953469261527e-06, "count": 1, "self": 1.2999953469261527e-06 }, "TrainerController._save_models": { "total": 2.995353799997247, "count": 1, "self": 0.07506540000031237, "children": { "RLTrainer._checkpoint": { "total": 2.9202883999969345, "count": 1, "self": 2.9202883999969345 } } } } } } }