poca-SoccerTwos / run_logs /timers.json
TayJen's picture
First Push
9554487 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.0050082206726074,
"min": 2.0050082206726074,
"max": 3.295748472213745,
"count": 502
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 40677.60546875,
"min": 20869.521484375,
"max": 119609.4453125,
"count": 502
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 54.955555555555556,
"min": 42.0948275862069,
"max": 999.0,
"count": 502
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19784.0,
"min": 9452.0,
"max": 30532.0,
"count": 502
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1477.117278201413,
"min": 1186.646782529152,
"max": 1495.5570804937465,
"count": 482
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 265881.11007625435,
"min": 2373.293565058304,
"max": 332334.32147909724,
"count": 482
},
"SoccerTwos.Step.mean": {
"value": 5019953.0,
"min": 9284.0,
"max": 5019953.0,
"count": 502
},
"SoccerTwos.Step.sum": {
"value": 5019953.0,
"min": 9284.0,
"max": 5019953.0,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.03396926447749138,
"min": -0.11507141590118408,
"max": 0.18107877671718597,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -6.148436546325684,
"min": -20.482711791992188,
"max": 21.93915367126465,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.035848017781972885,
"min": -0.1105540320277214,
"max": 0.17805613577365875,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -6.488491058349609,
"min": -19.678617477416992,
"max": 22.855632781982422,
"count": 502
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 502
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.11308287553365717,
"min": -0.5714285714285714,
"max": 0.7262333313624064,
"count": 502
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -20.46800047159195,
"min": -56.812400460243225,
"max": 50.44760024547577,
"count": 502
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.11308287553365717,
"min": -0.5714285714285714,
"max": 0.7262333313624064,
"count": 502
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -20.46800047159195,
"min": -56.812400460243225,
"max": 50.44760024547577,
"count": 502
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 502
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 502
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01837546599757237,
"min": 0.010520851605663968,
"max": 0.023146046899879973,
"count": 239
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01837546599757237,
"min": 0.010520851605663968,
"max": 0.023146046899879973,
"count": 239
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0992192804813385,
"min": 0.00021007875232802083,
"max": 0.1071329064667225,
"count": 239
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0992192804813385,
"min": 0.00021007875232802083,
"max": 0.1071329064667225,
"count": 239
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10061396136879922,
"min": 0.00021123107483920952,
"max": 0.1091360330581665,
"count": 239
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10061396136879922,
"min": 0.00021123107483920952,
"max": 0.1091360330581665,
"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": 0.2,
"max": 0.20000000000000007,
"count": 239
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 239
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 239
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 239
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1753884998",
"python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]",
"command_line_arguments": "/opt/homebrew/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1",
"numpy_version": "1.23.5",
"end_time_seconds": "1753963384"
},
"total": 16633.662456333004,
"count": 1,
"self": 0.2547951660089893,
"children": {
"run_training.setup": {
"total": 0.18008191699482268,
"count": 1,
"self": 0.18008191699482268
},
"TrainerController.start_learning": {
"total": 16633.22757925,
"count": 1,
"self": 3.0732997167579015,
"children": {
"TrainerController._reset_env": {
"total": 4.523681374041189,
"count": 26,
"self": 4.523681374041189
},
"TrainerController.advance": {
"total": 16625.535765451204,
"count": 338823,
"self": 2.6742347679901286,
"children": {
"env_step": {
"total": 13008.63882516577,
"count": 338823,
"self": 12505.456857441095,
"children": {
"SubprocessEnvManager._take_step": {
"total": 501.13629251778184,
"count": 338823,
"self": 14.931148002702685,
"children": {
"TorchPolicy.evaluate": {
"total": 486.20514451507916,
"count": 637422,
"self": 486.20514451507916
}
}
},
"workers": {
"total": 2.0456752068930655,
"count": 338822,
"self": 0.0,
"children": {
"worker_root": {
"total": 16625.852951579385,
"count": 338822,
"is_parallel": true,
"self": 4503.438406262714,
"children": {
"steps_from_proto": {
"total": 0.034171746992797125,
"count": 52,
"is_parallel": true,
"self": 0.003986415977124125,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.030185331015673,
"count": 208,
"is_parallel": true,
"self": 0.030185331015673
}
}
},
"UnityEnvironment.step": {
"total": 12122.380373569678,
"count": 338822,
"is_parallel": true,
"self": 32.76600961067743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 218.37995054922794,
"count": 338822,
"is_parallel": true,
"self": 218.37995054922794
},
"communicator.exchange": {
"total": 11438.194612325897,
"count": 338822,
"is_parallel": true,
"self": 11438.194612325897
},
"steps_from_proto": {
"total": 433.0398010838762,
"count": 677644,
"is_parallel": true,
"self": 47.15719438215456,
"children": {
"_process_rank_one_or_two_observation": {
"total": 385.88260670172167,
"count": 2710576,
"is_parallel": true,
"self": 385.88260670172167
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 3614.2227055174444,
"count": 338822,
"self": 26.15394951798953,
"children": {
"process_trajectory": {
"total": 642.4519175745081,
"count": 338822,
"self": 640.7957824495097,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6561351249984,
"count": 10,
"self": 1.6561351249984
}
}
},
"_update_policy": {
"total": 2945.6168384249468,
"count": 240,
"self": 282.1507665701356,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2663.466071854811,
"count": 7203,
"self": 2663.466071854811
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1601015254855156e-07,
"count": 1,
"self": 4.1601015254855156e-07
},
"TrainerController._save_models": {
"total": 0.09483229198667686,
"count": 1,
"self": 0.0023244579788297415,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09250783400784712,
"count": 1,
"self": 0.09250783400784712
}
}
}
}
}
}
}