{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8175519704818726, "min": 1.8140881061553955, "max": 3.295701503753662, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36525.5234375, "min": 22337.462890625, "max": 131874.515625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 47.53398058252427, "min": 38.330708661417326, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19584.0, "min": 16412.0, "max": 23556.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1603.824692115033, "min": 1194.096010161107, "max": 1605.1980019651173, "count": 489 }, "SoccerTwos.Self-play.ELO.sum": { "value": 330387.8865756968, "min": 2388.192020322214, "max": 406011.72053636017, "count": 489 }, "SoccerTwos.Step.mean": { "value": 4999973.0, "min": 9798.0, "max": 4999973.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999973.0, "min": 9798.0, "max": 4999973.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.07345908880233765, "min": -0.09888984262943268, "max": 0.21315433084964752, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 15.132572174072266, "min": -14.733272552490234, "max": 31.57974624633789, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.07349902391433716, "min": -0.09889479726552963, "max": 0.2176845520734787, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 15.140799522399902, "min": -15.715633392333984, "max": 31.43023681640625, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09891941680491549, "min": -0.6974260858867479, "max": 0.5235634401280392, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.37739986181259, "min": -50.82000017166138, "max": 65.04260015487671, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09891941680491549, "min": -0.6974260858867479, "max": 0.5235634401280392, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.37739986181259, "min": -50.82000017166138, "max": 65.04260015487671, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015070095177118976, "min": 0.009431918489281089, "max": 0.02361279058580597, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015070095177118976, "min": 0.009431918489281089, "max": 0.02361279058580597, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12243687783678373, "min": 0.0002465255400845005, "max": 0.1273724970718225, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12243687783678373, "min": 0.0002465255400845005, "max": 0.1273724970718225, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12491700227061907, "min": 0.0002474056674448851, "max": 0.12908415421843528, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12491700227061907, "min": 0.0002474056674448851, "max": 0.12908415421843528, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716182049", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716199207" }, "total": 14552.858227707, "count": 1, "self": 0.32714386499901593, "children": { "run_training.setup": { "total": 0.04076881100002083, "count": 1, "self": 0.04076881100002083 }, "TrainerController.start_learning": { "total": 14552.490315031, "count": 1, "self": 6.417697513355961, "children": { "TrainerController._reset_env": { "total": 5.1254225370011, "count": 25, "self": 5.1254225370011 }, "TrainerController.advance": { "total": 14540.675641536644, "count": 341391, "self": 6.997741897626838, "children": { "env_step": { "total": 11577.941410467896, "count": 341391, "self": 4996.015263816564, "children": { "SubprocessEnvManager._take_step": { "total": 6577.59461979787, "count": 341391, "self": 44.07531883835691, "children": { "TorchPolicy.evaluate": { "total": 6533.519300959513, "count": 633074, "self": 6533.519300959513 } } }, "workers": { "total": 4.331526853462037, "count": 341391, "self": 0.0, "children": { "worker_root": { "total": 14536.62526502233, "count": 341391, "is_parallel": true, "self": 10275.698606395592, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024190549999048017, "count": 2, "is_parallel": true, "self": 0.001150909000102729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012681459998020728, "count": 8, "is_parallel": true, "self": 0.0012681459998020728 } } }, "UnityEnvironment.step": { "total": 0.021684106999941832, "count": 1, "is_parallel": true, "self": 0.0004135299999461495, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004154700000071898, "count": 1, "is_parallel": true, "self": 0.0004154700000071898 }, "communicator.exchange": { "total": 0.01965673600000173, "count": 1, "is_parallel": true, "self": 0.01965673600000173 }, "steps_from_proto": { "total": 0.0011983709999867642, "count": 2, "is_parallel": true, "self": 0.0002674179999075932, "children": { "_process_rank_one_or_two_observation": { "total": 0.000930953000079171, "count": 8, "is_parallel": true, "self": 0.000930953000079171 } } } } } } }, "UnityEnvironment.step": { "total": 4260.8943745997385, "count": 341390, "is_parallel": true, "self": 138.99753204706485, "children": { "UnityEnvironment._generate_step_input": { "total": 84.16560661164522, "count": 341390, "is_parallel": true, "self": 84.16560661164522 }, "communicator.exchange": { "total": 3632.4614862938615, "count": 341390, "is_parallel": true, "self": 3632.4614862938615 }, "steps_from_proto": { "total": 405.2697496471668, "count": 682780, "is_parallel": true, "self": 92.00081552158917, "children": { "_process_rank_one_or_two_observation": { "total": 313.26893412557763, "count": 2731120, "is_parallel": true, "self": 313.26893412557763 } } } } }, "steps_from_proto": { "total": 0.03228402700096922, "count": 48, "is_parallel": true, "self": 0.007439848004196392, "children": { "_process_rank_one_or_two_observation": { "total": 0.024844178996772825, "count": 192, "is_parallel": true, "self": 0.024844178996772825 } } } } } } } } }, "trainer_advance": { "total": 2955.73648917112, "count": 341391, "self": 47.368284518879136, "children": { "process_trajectory": { "total": 1788.9564993552522, "count": 341391, "self": 1785.8742582572481, "children": { "RLTrainer._checkpoint": { "total": 3.082241098004033, "count": 10, "self": 3.082241098004033 } } }, "_update_policy": { "total": 1119.4117052969884, "count": 239, "self": 505.23970683903906, "children": { "TorchPOCAOptimizer.update": { "total": 614.1719984579494, "count": 7170, "self": 614.1719984579494 } } } } } } }, "trainer_threads": { "total": 5.149995558895171e-07, "count": 1, "self": 5.149995558895171e-07 }, "TrainerController._save_models": { "total": 0.27155292899988126, "count": 1, "self": 0.0022321679989545373, "children": { "RLTrainer._checkpoint": { "total": 0.2693207610009267, "count": 1, "self": 0.2693207610009267 } } } } } } }