poca-SoccerTwos / run_logs /timers.json
jimjiang203's picture
First Push
05783cd verified
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.0103368759155273,
"min": 1.9777865409851074,
"max": 3.2957277297973633,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38662.80078125,
"min": 14614.603515625,
"max": 120638.7265625,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 70.3768115942029,
"min": 51.09375,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19424.0,
"min": 15784.0,
"max": 27088.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1564.4432060772401,
"min": 1176.7258691064465,
"max": 1580.0330219178438,
"count": 492
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 215893.16243865914,
"min": 2355.6993006599496,
"max": 290868.49722051993,
"count": 492
},
"SoccerTwos.Step.mean": {
"value": 4999970.0,
"min": 9560.0,
"max": 4999970.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999970.0,
"min": 9560.0,
"max": 4999970.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.060075994580984116,
"min": -0.10495267808437347,
"max": 0.1653749793767929,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -8.290487289428711,
"min": -16.626325607299805,
"max": 27.782997131347656,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.06104997918009758,
"min": -0.10382936894893646,
"max": 0.1679215431213379,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -8.424897193908691,
"min": -16.265779495239258,
"max": 28.210819244384766,
"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": -0.13375362278758615,
"min": -0.8823529411764706,
"max": 0.41410149211314184,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -18.45799994468689,
"min": -41.70920014381409,
"max": 50.97639989852905,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.13375362278758615,
"min": -0.8823529411764706,
"max": 0.41410149211314184,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -18.45799994468689,
"min": -41.70920014381409,
"max": 50.97639989852905,
"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": 0.015407767969494064,
"min": 0.011601856948497394,
"max": 0.024236328400244627,
"count": 239
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.015407767969494064,
"min": 0.011601856948497394,
"max": 0.024236328400244627,
"count": 239
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.08410224045316378,
"min": 0.0001900104902839909,
"max": 0.10161295259992281,
"count": 239
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.08410224045316378,
"min": 0.0001900104902839909,
"max": 0.10161295259992281,
"count": 239
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.08507756615678469,
"min": 0.00019070169025023158,
"max": 0.10369378998875618,
"count": 239
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.08507756615678469,
"min": 0.00019070169025023158,
"max": 0.10369378998875618,
"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": "1723712147",
"python_version": "3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0]",
"command_line_arguments": "/root/miniconda3/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1723724501"
},
"total": 12354.318006377667,
"count": 1,
"self": 0.42288713436573744,
"children": {
"run_training.setup": {
"total": 0.034789071418344975,
"count": 1,
"self": 0.034789071418344975
},
"TrainerController.start_learning": {
"total": 12353.860330171883,
"count": 1,
"self": 5.262380417436361,
"children": {
"TrainerController._reset_env": {
"total": 2.691625320352614,
"count": 21,
"self": 2.691625320352614
},
"TrainerController.advance": {
"total": 12345.807688859291,
"count": 333227,
"self": 4.828748322091997,
"children": {
"env_step": {
"total": 11043.155604165979,
"count": 333227,
"self": 10145.747690772638,
"children": {
"SubprocessEnvManager._take_step": {
"total": 893.9432374471799,
"count": 333227,
"self": 37.65499076526612,
"children": {
"TorchPolicy.evaluate": {
"total": 856.2882466819137,
"count": 632172,
"self": 856.2882466819137
}
}
},
"workers": {
"total": 3.464675946161151,
"count": 333227,
"self": 0.0,
"children": {
"worker_root": {
"total": 12330.256846216507,
"count": 333227,
"is_parallel": true,
"self": 3141.1514767790213,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007085210643708706,
"count": 2,
"is_parallel": true,
"self": 0.0016971677541732788,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005388042889535427,
"count": 8,
"is_parallel": true,
"self": 0.005388042889535427
}
}
},
"UnityEnvironment.step": {
"total": 0.04877493344247341,
"count": 1,
"is_parallel": true,
"self": 0.0017983177676796913,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.001361580565571785,
"count": 1,
"is_parallel": true,
"self": 0.001361580565571785
},
"communicator.exchange": {
"total": 0.04070513695478439,
"count": 1,
"is_parallel": true,
"self": 0.04070513695478439
},
"steps_from_proto": {
"total": 0.004909898154437542,
"count": 2,
"is_parallel": true,
"self": 0.0010248394683003426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038850586861371994,
"count": 8,
"is_parallel": true,
"self": 0.0038850586861371994
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 9189.011991587467,
"count": 333226,
"is_parallel": true,
"self": 515.4125970257446,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 333.63409104477614,
"count": 333226,
"is_parallel": true,
"self": 333.63409104477614
},
"communicator.exchange": {
"total": 6891.873233468272,
"count": 333226,
"is_parallel": true,
"self": 6891.873233468272
},
"steps_from_proto": {
"total": 1448.092070048675,
"count": 666452,
"is_parallel": true,
"self": 286.7437717281282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1161.3482983205467,
"count": 2665808,
"is_parallel": true,
"self": 1161.3482983205467
}
}
}
}
},
"steps_from_proto": {
"total": 0.09337785001844168,
"count": 40,
"is_parallel": true,
"self": 0.01847281027585268,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.074905039742589,
"count": 160,
"is_parallel": true,
"self": 0.074905039742589
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1297.8233363712206,
"count": 333227,
"self": 48.36833060905337,
"children": {
"process_trajectory": {
"total": 449.7733397288248,
"count": 333227,
"self": 448.74016169831157,
"children": {
"RLTrainer._checkpoint": {
"total": 1.033178030513227,
"count": 10,
"self": 1.033178030513227
}
}
},
"_update_policy": {
"total": 799.6816660333425,
"count": 239,
"self": 540.5786511749029,
"children": {
"TorchPOCAOptimizer.update": {
"total": 259.10301485843956,
"count": 7170,
"self": 259.10301485843956
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.537884473800659e-07,
"count": 1,
"self": 6.537884473800659e-07
},
"TrainerController._save_models": {
"total": 0.09863492101430893,
"count": 1,
"self": 0.0014009485021233559,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09723397251218557,
"count": 1,
"self": 0.09723397251218557
}
}
}
}
}
}
}