poca-SoccerTwos / run_logs /timers.json
codeSpaghetti's picture
First Push
94bfc32
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.309561014175415,
"min": 2.281111478805542,
"max": 3.2957603931427,
"count": 394
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 43974.04296875,
"min": 18621.85546875,
"max": 132478.5,
"count": 394
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 50.45360824742268,
"min": 44.34234234234234,
"max": 999.0,
"count": 394
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19576.0,
"min": 14472.0,
"max": 26132.0,
"count": 394
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1355.5547328663977,
"min": 1170.5394824436014,
"max": 1377.3069070113052,
"count": 380
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 262977.61817608116,
"min": 2361.320079440623,
"max": 298231.5035719138,
"count": 380
},
"SoccerTwos.Step.mean": {
"value": 3939974.0,
"min": 9082.0,
"max": 3939974.0,
"count": 394
},
"SoccerTwos.Step.sum": {
"value": 3939974.0,
"min": 9082.0,
"max": 3939974.0,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.041746560484170914,
"min": -0.11274479329586029,
"max": 0.1803084909915924,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -8.140579223632812,
"min": -17.926422119140625,
"max": 26.505348205566406,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.040217842906713486,
"min": -0.10436349362134933,
"max": 0.17117635905742645,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -7.842479705810547,
"min": -17.932662963867188,
"max": 24.61751937866211,
"count": 394
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 394
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.0719497439188835,
"min": -0.625,
"max": 0.46092973206494303,
"count": 394
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -14.030200064182281,
"min": -33.70920014381409,
"max": 45.10700011253357,
"count": 394
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.0719497439188835,
"min": -0.625,
"max": 0.46092973206494303,
"count": 394
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -14.030200064182281,
"min": -33.70920014381409,
"max": 45.10700011253357,
"count": 394
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 394
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 394
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.014392319566104561,
"min": 0.010217342836161455,
"max": 0.025237433375635495,
"count": 187
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.014392319566104561,
"min": 0.010217342836161455,
"max": 0.025237433375635495,
"count": 187
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09865847503145536,
"min": 0.00013014958870674793,
"max": 0.10634844924012819,
"count": 187
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09865847503145536,
"min": 0.00013014958870674793,
"max": 0.10634844924012819,
"count": 187
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10076268985867501,
"min": 0.00012500778199561562,
"max": 0.1087349534034729,
"count": 187
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10076268985867501,
"min": 0.00012500778199561562,
"max": 0.1087349534034729,
"count": 187
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 187
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 187
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 187
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 187
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 187
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 187
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679247432",
"python_version": "3.9.16 (main, Mar 8 2023, 04:29:24) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/alessio/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1679262837"
},
"total": 15331.936170459,
"count": 1,
"self": 0.1366623760004586,
"children": {
"run_training.setup": {
"total": 0.1844646249999995,
"count": 1,
"self": 0.1844646249999995
},
"TrainerController.start_learning": {
"total": 15331.615043458,
"count": 1,
"self": 3.0446913397772732,
"children": {
"TrainerController._reset_env": {
"total": 2.8925383340009363,
"count": 20,
"self": 2.8925383340009363
},
"TrainerController.advance": {
"total": 15325.58360245022,
"count": 262919,
"self": 3.028552508651046,
"children": {
"env_step": {
"total": 12431.596222326261,
"count": 262919,
"self": 11982.406396551347,
"children": {
"SubprocessEnvManager._take_step": {
"total": 447.1306771715281,
"count": 262919,
"self": 12.720688878481383,
"children": {
"TorchPolicy.evaluate": {
"total": 434.4099882930467,
"count": 503569,
"self": 434.4099882930467
}
}
},
"workers": {
"total": 2.059148603387108,
"count": 262918,
"self": 0.0,
"children": {
"worker_root": {
"total": 15323.905628031922,
"count": 262918,
"is_parallel": true,
"self": 3780.745046928694,
"children": {
"steps_from_proto": {
"total": 0.030383457991041363,
"count": 40,
"is_parallel": true,
"self": 0.0034091219993073185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.026974335991734044,
"count": 160,
"is_parallel": true,
"self": 0.026974335991734044
}
}
},
"UnityEnvironment.step": {
"total": 11543.130197645236,
"count": 262918,
"is_parallel": true,
"self": 31.898869138076407,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 194.25133372881731,
"count": 262918,
"is_parallel": true,
"self": 194.25133372881731
},
"communicator.exchange": {
"total": 10895.712968361237,
"count": 262918,
"is_parallel": true,
"self": 10895.712968361237
},
"steps_from_proto": {
"total": 421.2670264171064,
"count": 525836,
"is_parallel": true,
"self": 46.50732735628554,
"children": {
"_process_rank_one_or_two_observation": {
"total": 374.7596990608209,
"count": 2103344,
"is_parallel": true,
"self": 374.7596990608209
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2890.958827615309,
"count": 262918,
"self": 24.60439574676002,
"children": {
"process_trajectory": {
"total": 572.0797707045465,
"count": 262918,
"self": 571.4511638295482,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6286068749982405,
"count": 7,
"self": 0.6286068749982405
}
}
},
"_update_policy": {
"total": 2294.2746611640027,
"count": 187,
"self": 307.0505535550551,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1987.2241076089476,
"count": 5610,
"self": 1987.2241076089476
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.420006345957518e-07,
"count": 1,
"self": 5.420006345957518e-07
},
"TrainerController._save_models": {
"total": 0.09421079200001259,
"count": 1,
"self": 0.0013693340006284416,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09284145799938415,
"count": 1,
"self": 0.09284145799938415
}
}
}
}
}
}
}