{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.5375173091888428, "min": 2.478060007095337, "max": 3.2453742027282715, "count": 116 }, "SoccerTwos.Policy.Entropy.sum": { "value": 508802.6875, "min": 499868.875, "max": 705045.0625, "count": 116 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.175496688741724, "min": 47.84848484848485, "max": 873.719298245614, "count": 116 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 196332.0, "min": 175024.0, "max": 201616.0, "count": 116 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1723.5295705270155, "min": 1200.761697765363, "max": 1750.0066665760548, "count": 116 }, "SoccerTwos.Self-play.ELO.sum": { "value": 3123035.581794952, "min": 28899.408271907938, "max": 3337045.459913326, "count": 116 }, "SoccerTwos.Step.mean": { "value": 15099986.0, "min": 3599544.0, "max": 15099986.0, "count": 116 }, "SoccerTwos.Step.sum": { "value": 15099986.0, "min": 3599544.0, "max": 15099986.0, "count": 116 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.06375407427549362, "min": -0.016356362029910088, "max": 0.23395289480686188, "count": 116 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 115.52238464355469, "min": -2.895076036453247, "max": 379.1238708496094, "count": 116 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.062257301062345505, "min": -0.01666545681655407, "max": 0.23140472173690796, "count": 116 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 112.81022644042969, "min": -2.9497857093811035, "max": 376.95770263671875, "count": 116 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 116 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 116 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.07598189789201513, "min": -0.1950943389872335, "max": 0.4234046910034596, "count": 116 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 137.67919898033142, "min": -28.453200340270996, "max": 698.6883994340897, "count": 116 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.07598189789201513, "min": -0.1950943389872335, "max": 0.4234046910034596, "count": 116 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 137.67919898033142, "min": -28.453200340270996, "max": 698.6883994340897, "count": 116 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019614993249997496, "min": 0.013303355816818414, "max": 0.019884867273115864, "count": 116 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.09807496624998747, "min": 0.05321342326727366, "max": 0.09942433636557932, "count": 116 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.06939018179972967, "min": 0.0009417598268555593, "max": 0.07270204136768979, "count": 116 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.34695090899864833, "min": 0.003767039307422237, "max": 0.3635102068384489, "count": 116 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07017512281735738, "min": 0.0009412774349281487, "max": 0.07344284377992152, "count": 116 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.3508756140867869, "min": 0.003765109739712595, "max": 0.36721421889960765, "count": 116 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0001849456679271698, "min": 0.0001849456679271698, "max": 0.00019643284378357905, "count": 116 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0009247283396358489, "min": 0.0007417988211006043, "max": 0.0009812514913742588, "count": 116 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25, "min": 0.25, "max": 0.25, "count": 116 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 1.25, "min": 1.0, "max": 1.25, "count": 116 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.009248035736980001, "min": 0.009248035736980001, "max": 0.009821820457900001, "count": 116 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.046240178684900005, "min": 0.0370928496604, "max": 0.049063511525899994, "count": 116 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 116 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 116 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693645763", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\Giuseppe\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1693687959" }, "total": 42195.420038699995, "count": 1, "self": 5.344371200000751, "children": { "run_training.setup": { "total": 0.21789530000000035, "count": 1, "self": 0.21789530000000035 }, "TrainerController.start_learning": { "total": 42189.8577722, "count": 1, "self": 21.40683080162853, "children": { "TrainerController._reset_env": { "total": 8.697414299989346, "count": 59, "self": 8.697414299989346 }, "TrainerController.advance": { "total": 42159.54521549838, "count": 799049, "self": 22.4155723015283, "children": { "env_step": { "total": 15654.42198469873, "count": 799049, "self": 12022.189401201565, "children": { "SubprocessEnvManager._take_step": { "total": 3618.707046797893, "count": 799049, "self": 125.06815719666793, "children": { "TorchPolicy.evaluate": { "total": 3493.638889601225, "count": 1460952, "self": 3493.638889601225 } } }, "workers": { "total": 13.525536699272141, "count": 799048, "self": 0.0, "children": { "worker_root": { "total": 42153.45278110403, "count": 799048, "is_parallel": true, "self": 32449.08701390442, "children": { "steps_from_proto": { "total": 0.09829320002441388, "count": 118, "is_parallel": true, "self": 0.02209340001842719, "children": { "_process_rank_one_or_two_observation": { "total": 0.0761998000059867, "count": 472, "is_parallel": true, "self": 0.0761998000059867 } } }, "UnityEnvironment.step": { "total": 9704.267473999587, "count": 799048, "is_parallel": true, "self": 448.13597820102405, "children": { "UnityEnvironment._generate_step_input": { "total": 379.29707640063845, "count": 799048, "is_parallel": true, "self": 379.29707640063845 }, "communicator.exchange": { "total": 7440.3215328005945, "count": 799048, "is_parallel": true, "self": 7440.3215328005945 }, "steps_from_proto": { "total": 1436.51288659733, "count": 1598096, "is_parallel": true, "self": 321.8152367985181, "children": { "_process_rank_one_or_two_observation": { "total": 1114.6976497988119, "count": 6392384, "is_parallel": true, "self": 1114.6976497988119 } } } } } } } } } } }, "trainer_advance": { "total": 26482.70765849812, "count": 799048, "self": 160.04978299760842, "children": { "process_trajectory": { "total": 4205.995983800536, "count": 799048, "self": 4204.443525000541, "children": { "RLTrainer._checkpoint": { "total": 1.552458799994838, "count": 6, "self": 1.552458799994838 } } }, "_update_policy": { "total": 22116.661891699976, "count": 561, "self": 1938.0092438998654, "children": { "TorchPOCAOptimizer.update": { "total": 20178.65264780011, "count": 16830, "self": 20178.65264780011 } } } } } } }, "trainer_threads": { "total": 2.7999994927085936e-06, "count": 1, "self": 2.7999994927085936e-06 }, "TrainerController._save_models": { "total": 0.20830879999994067, "count": 1, "self": 0.01186030000098981, "children": { "RLTrainer._checkpoint": { "total": 0.19644849999895087, "count": 1, "self": 0.19644849999895087 } } } } } } }