poca-SoccerTwos / run_logs /timers.json
EricValen's picture
First Push
7fbfbf0 verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.6124267578125,
"min": 1.5322037935256958,
"max": 3.295731544494629,
"count": 1000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 31268.1796875,
"min": 16448.52734375,
"max": 162302.734375,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 54.4,
"min": 41.73504273504273,
"max": 999.0,
"count": 1000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19584.0,
"min": 11868.0,
"max": 27432.0,
"count": 1000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1659.5371078323737,
"min": 1197.050779918932,
"max": 1680.5815491029825,
"count": 960
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 298716.6794098273,
"min": 2396.1238497321574,
"max": 377547.2199248422,
"count": 960
},
"SoccerTwos.Step.mean": {
"value": 9999877.0,
"min": 9738.0,
"max": 9999877.0,
"count": 1000
},
"SoccerTwos.Step.sum": {
"value": 9999877.0,
"min": 9738.0,
"max": 9999877.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.0024716106709092855,
"min": -0.12637822329998016,
"max": 0.17084462940692902,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.4448899030685425,
"min": -21.040916442871094,
"max": 28.765628814697266,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.004061748739331961,
"min": -0.1250016838312149,
"max": 0.16629882156848907,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.7311147451400757,
"min": -21.22384262084961,
"max": 30.678293228149414,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.00823777847819858,
"min": -0.75,
"max": 0.6355263198676863,
"count": 1000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -1.4828001260757446,
"min": -57.12580007314682,
"max": 63.9301997423172,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.00823777847819858,
"min": -0.75,
"max": 0.6355263198676863,
"count": 1000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -1.4828001260757446,
"min": -57.12580007314682,
"max": 63.9301997423172,
"count": 1000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01586581016648173,
"min": 0.010011313502521565,
"max": 0.026430096075637267,
"count": 481
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01586581016648173,
"min": 0.010011313502521565,
"max": 0.026430096075637267,
"count": 481
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10227966184417407,
"min": 9.375683627392088e-07,
"max": 0.12788183813293774,
"count": 481
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10227966184417407,
"min": 9.375683627392088e-07,
"max": 0.12788183813293774,
"count": 481
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10316868474086126,
"min": 1.0141310099243127e-06,
"max": 0.12964529618620874,
"count": 481
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10316868474086126,
"min": 1.0141310099243127e-06,
"max": 0.12964529618620874,
"count": 481
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 481
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 481
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 481
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 481
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 481
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 481
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1709322476",
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "\\\\?\\C:\\Users\\valen\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cpu",
"numpy_version": "1.23.5",
"end_time_seconds": "1709376645"
},
"total": 54168.1737142,
"count": 1,
"self": 1.3483520000008866,
"children": {
"run_training.setup": {
"total": 0.4220677000002979,
"count": 1,
"self": 0.4220677000002979
},
"TrainerController.start_learning": {
"total": 54166.4032945,
"count": 1,
"self": 25.984264403028646,
"children": {
"TrainerController._reset_env": {
"total": 26.09978190001675,
"count": 50,
"self": 26.09978190001675
},
"TrainerController.advance": {
"total": 54114.111424096955,
"count": 685712,
"self": 25.490667992642557,
"children": {
"env_step": {
"total": 18393.871346600725,
"count": 685712,
"self": 13763.417653097986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4613.097430001363,
"count": 685712,
"self": 169.79468140280278,
"children": {
"TorchPolicy.evaluate": {
"total": 4443.30274859856,
"count": 1263434,
"self": 4443.30274859856
}
}
},
"workers": {
"total": 17.356263501376816,
"count": 685712,
"self": 0.0,
"children": {
"worker_root": {
"total": 54110.41351849818,
"count": 685712,
"is_parallel": true,
"self": 43633.03810960043,
"children": {
"steps_from_proto": {
"total": 0.16289969999070308,
"count": 100,
"is_parallel": true,
"self": 0.03206340001906938,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.1308362999716337,
"count": 400,
"is_parallel": true,
"self": 0.1308362999716337
}
}
},
"UnityEnvironment.step": {
"total": 10477.212509197756,
"count": 685712,
"is_parallel": true,
"self": 636.8695216940359,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 643.4190385017737,
"count": 685712,
"is_parallel": true,
"self": 643.4190385017737
},
"communicator.exchange": {
"total": 7085.539716603209,
"count": 685712,
"is_parallel": true,
"self": 7085.539716603209
},
"steps_from_proto": {
"total": 2111.3842323987374,
"count": 1371424,
"is_parallel": true,
"self": 428.9303403986569,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1682.4538920000805,
"count": 5485696,
"is_parallel": true,
"self": 1682.4538920000805
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 35694.74940950359,
"count": 685712,
"self": 177.5910707027724,
"children": {
"process_trajectory": {
"total": 6254.872241500784,
"count": 685712,
"self": 6250.621955000784,
"children": {
"RLTrainer._checkpoint": {
"total": 4.250286500000584,
"count": 20,
"self": 4.250286500000584
}
}
},
"_update_policy": {
"total": 29262.28609730003,
"count": 481,
"self": 2467.6258165006147,
"children": {
"TorchPOCAOptimizer.update": {
"total": 26794.660280799417,
"count": 14433,
"self": 26794.660280799417
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5999976312741637e-06,
"count": 1,
"self": 1.5999976312741637e-06
},
"TrainerController._save_models": {
"total": 0.20782250000047497,
"count": 1,
"self": 0.012669900002947543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19515259999752743,
"count": 1,
"self": 0.19515259999752743
}
}
}
}
}
}
}