poca-SoccerTwos / run_logs /timers.json
yingzhi's picture
First Push
5bc64e9
raw
history blame
20.2 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.7294182777404785,
"min": 1.4730992317199707,
"max": 2.8711423873901367,
"count": 3466
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 36193.265625,
"min": 1450.902099609375,
"max": 102361.5390625,
"count": 3466
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 92.24074074074075,
"min": 53.26086956521739,
"max": 999.0,
"count": 3466
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19924.0,
"min": 2284.0,
"max": 31968.0,
"count": 3466
},
"SoccerTwos.Step.mean": {
"value": 49999866.0,
"min": 14519686.0,
"max": 49999866.0,
"count": 3549
},
"SoccerTwos.Step.sum": {
"value": 49999866.0,
"min": 14519686.0,
"max": 49999866.0,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.01551780290901661,
"min": -0.13659553229808807,
"max": 0.11925806105136871,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -1.6759227514266968,
"min": -18.986778259277344,
"max": 16.75717544555664,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.018236050382256508,
"min": -0.13535547256469727,
"max": 0.12039851397275925,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -1.9694933891296387,
"min": -18.814411163330078,
"max": 16.86180305480957,
"count": 3549
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 3549
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.035122224578151,
"min": -0.725433332224687,
"max": 0.3837440013885498,
"count": 3549
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -3.7932002544403076,
"min": -53.077200174331665,
"max": 46.353999853134155,
"count": 3549
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.035122224578151,
"min": -0.725433332224687,
"max": 0.3837440013885498,
"count": 3549
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -3.7932002544403076,
"min": -53.077200174331665,
"max": 46.353999853134155,
"count": 3549
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3549
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3549
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.021713513980891243,
"min": 0.011342559655895456,
"max": 0.025571691037233297,
"count": 1631
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.021713513980891243,
"min": 0.011342559655895456,
"max": 0.025571691037233297,
"count": 1631
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.08178103417158127,
"min": 1.3015488363003296e-10,
"max": 0.09387121895949045,
"count": 1631
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.08178103417158127,
"min": 1.3015488363003296e-10,
"max": 0.09387121895949045,
"count": 1631
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0829097809890906,
"min": 1.6300951560799248e-10,
"max": 0.09618829761942228,
"count": 1631
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0829097809890906,
"min": 1.6300951560799248e-10,
"max": 0.09618829761942228,
"count": 1631
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 1631
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 1631
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.19999999999999993,
"max": 0.20000000000000007,
"count": 1631
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.19999999999999993,
"max": 0.20000000000000007,
"count": 1631
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 1631
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 1631
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1828.001218305057,
"min": 1200.0001498125655,
"max": 1856.484432193121,
"count": 2680
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 197424.13157694615,
"min": 2400.000299625131,
"max": 339280.29181375104,
"count": 2680
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1682419437",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/ywang/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682492161"
},
"total": 72724.35209834576,
"count": 1,
"self": 0.430398958735168,
"children": {
"run_training.setup": {
"total": 0.013815724290907383,
"count": 1,
"self": 0.013815724290907383
},
"TrainerController.start_learning": {
"total": 72723.90788366273,
"count": 1,
"self": 32.2913175644353,
"children": {
"TrainerController._reset_env": {
"total": 9.365834064781666,
"count": 178,
"self": 9.365834064781666
},
"TrainerController.advance": {
"total": 72682.06993211806,
"count": 2360909,
"self": 30.575236765667796,
"children": {
"env_step": {
"total": 59991.325887230225,
"count": 2360909,
"self": 44835.31112164818,
"children": {
"SubprocessEnvManager._take_step": {
"total": 15135.870935967192,
"count": 2360909,
"self": 218.10892355814576,
"children": {
"TorchPolicy.evaluate": {
"total": 14917.762012409046,
"count": 4480876,
"self": 14917.762012409046
}
}
},
"workers": {
"total": 20.14382961485535,
"count": 2360909,
"self": 0.0,
"children": {
"worker_root": {
"total": 72623.26484198216,
"count": 2360909,
"is_parallel": true,
"self": 32826.15999284573,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002300834283232689,
"count": 2,
"is_parallel": true,
"self": 0.00044528860598802567,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018555456772446632,
"count": 8,
"is_parallel": true,
"self": 0.0018555456772446632
}
}
},
"UnityEnvironment.step": {
"total": 0.036706763319671154,
"count": 1,
"is_parallel": true,
"self": 0.001371915452182293,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009810281917452812,
"count": 1,
"is_parallel": true,
"self": 0.0009810281917452812
},
"communicator.exchange": {
"total": 0.030282161198556423,
"count": 1,
"is_parallel": true,
"self": 0.030282161198556423
},
"steps_from_proto": {
"total": 0.004071658477187157,
"count": 2,
"is_parallel": true,
"self": 0.0006186086684465408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003453049808740616,
"count": 8,
"is_parallel": true,
"self": 0.003453049808740616
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.5935418782755733,
"count": 354,
"is_parallel": true,
"self": 0.08555437345057726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.507987504824996,
"count": 1416,
"is_parallel": true,
"self": 0.507987504824996
}
}
},
"UnityEnvironment.step": {
"total": 39796.51130725816,
"count": 2360908,
"is_parallel": true,
"self": 2528.4048364218324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1444.7381926830858,
"count": 2360908,
"is_parallel": true,
"self": 1444.7381926830858
},
"communicator.exchange": {
"total": 28698.075794393197,
"count": 2360908,
"is_parallel": true,
"self": 28698.075794393197
},
"steps_from_proto": {
"total": 7125.292483760044,
"count": 4721816,
"is_parallel": true,
"self": 1002.5296536339447,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6122.762830126099,
"count": 18887264,
"is_parallel": true,
"self": 6122.762830126099
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 12660.168808122166,
"count": 2360909,
"self": 316.5947243180126,
"children": {
"process_trajectory": {
"total": 4475.142794431187,
"count": 2360909,
"self": 4453.203862401657,
"children": {
"RLTrainer._checkpoint": {
"total": 21.938932029530406,
"count": 71,
"self": 21.938932029530406
}
}
},
"_update_policy": {
"total": 7868.431289372966,
"count": 1631,
"self": 5279.163390261121,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2589.2678991118446,
"count": 50925,
"self": 2589.2678991118446
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.599592208862305e-07,
"count": 1,
"self": 7.599592208862305e-07
},
"TrainerController._save_models": {
"total": 0.18079915549606085,
"count": 1,
"self": 0.0018941247835755348,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1789050307124853,
"count": 1,
"self": 0.1789050307124853
}
}
}
}
}
}
}