beibeif's picture
First Push
77288fa verified
raw
history blame
20.2 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.953821063041687,
"min": 1.8360395431518555,
"max": 3.2957701683044434,
"count": 2000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 40764.5234375,
"min": 15148.421875,
"max": 150869.625,
"count": 2000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 61.9125,
"min": 36.71969696969697,
"max": 999.0,
"count": 2000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19812.0,
"min": 16324.0,
"max": 25460.0,
"count": 2000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1491.7116693595483,
"min": 1181.2097928802395,
"max": 1509.8147293466548,
"count": 1933
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 238673.86709752772,
"min": 2362.7470600107745,
"max": 390666.0517786308,
"count": 1933
},
"SoccerTwos.Step.mean": {
"value": 19999970.0,
"min": 9748.0,
"max": 19999970.0,
"count": 2000
},
"SoccerTwos.Step.sum": {
"value": 19999970.0,
"min": 9748.0,
"max": 19999970.0,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.013983321376144886,
"min": -0.11188939958810806,
"max": 0.14131636917591095,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -2.2373313903808594,
"min": -21.442651748657227,
"max": 20.897668838500977,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.013222572393715382,
"min": -0.11129643023014069,
"max": 0.14043569564819336,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -2.1156115531921387,
"min": -21.943002700805664,
"max": 22.116891860961914,
"count": 2000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.03847750276327133,
"min": -0.6666666666666666,
"max": 0.4657187480479479,
"count": 2000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 6.156400442123413,
"min": -61.22060042619705,
"max": 64.98719954490662,
"count": 2000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.03847750276327133,
"min": -0.6666666666666666,
"max": 0.4657187480479479,
"count": 2000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 6.156400442123413,
"min": -61.22060042619705,
"max": 64.98719954490662,
"count": 2000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 2000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.010737808815125998,
"min": 0.005027929565403611,
"max": 0.020201207045465706,
"count": 960
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.010737808815125998,
"min": 0.005027929565403611,
"max": 0.020201207045465706,
"count": 960
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.10132837543884914,
"min": 1.5233589768589204e-06,
"max": 0.13846134146054587,
"count": 960
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.10132837543884914,
"min": 1.5233589768589204e-06,
"max": 0.13846134146054587,
"count": 960
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.10244849969943365,
"min": 1.6686742810634313e-06,
"max": 0.14102613031864167,
"count": 960
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.10244849969943365,
"min": 1.6686742810634313e-06,
"max": 0.14102613031864167,
"count": 960
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 960
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 960
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 960
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 960
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 960
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 960
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1705757198",
"python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./../input/soccerfinal/SoccerTwos.yaml --env=./ml-agents/trained-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=Soccer --no-graphics",
"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": "1705800035"
},
"total": 42836.813690111,
"count": 1,
"self": 0.3314620749952155,
"children": {
"run_training.setup": {
"total": 0.09841409399996337,
"count": 1,
"self": 0.09841409399996337
},
"TrainerController.start_learning": {
"total": 42836.383813942004,
"count": 1,
"self": 31.16820587838447,
"children": {
"TrainerController._reset_env": {
"total": 7.336992975992871,
"count": 100,
"self": 7.336992975992871
},
"TrainerController.advance": {
"total": 42797.65524656562,
"count": 1361678,
"self": 33.933481584601395,
"children": {
"env_step": {
"total": 31111.48385727351,
"count": 1361678,
"self": 23554.45710108044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 7536.9110729506265,
"count": 1361678,
"self": 220.90544398053498,
"children": {
"TorchPolicy.evaluate": {
"total": 7316.0056289700915,
"count": 2528490,
"self": 7316.0056289700915
}
}
},
"workers": {
"total": 20.11568324244331,
"count": 1361678,
"self": 0.0,
"children": {
"worker_root": {
"total": 42786.915158091026,
"count": 1361678,
"is_parallel": true,
"self": 23799.42821186385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004608822000022883,
"count": 2,
"is_parallel": true,
"self": 0.0011540760000343653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0034547459999885177,
"count": 8,
"is_parallel": true,
"self": 0.0034547459999885177
}
}
},
"UnityEnvironment.step": {
"total": 0.03137612699993042,
"count": 1,
"is_parallel": true,
"self": 0.0007355089998100084,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0006529350000619161,
"count": 1,
"is_parallel": true,
"self": 0.0006529350000619161
},
"communicator.exchange": {
"total": 0.027124995999997736,
"count": 1,
"is_parallel": true,
"self": 0.027124995999997736
},
"steps_from_proto": {
"total": 0.0028626870000607596,
"count": 2,
"is_parallel": true,
"self": 0.0005997199998546421,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022629670002061175,
"count": 8,
"is_parallel": true,
"self": 0.0022629670002061175
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 18987.215949916157,
"count": 1361677,
"is_parallel": true,
"self": 999.5017485719763,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 825.9811654139888,
"count": 1361677,
"is_parallel": true,
"self": 825.9811654139888
},
"communicator.exchange": {
"total": 13345.161397115104,
"count": 1361677,
"is_parallel": true,
"self": 13345.161397115104
},
"steps_from_proto": {
"total": 3816.571638815089,
"count": 2723354,
"is_parallel": true,
"self": 649.0959179964229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3167.475720818666,
"count": 10893416,
"is_parallel": true,
"self": 3167.475720818666
}
}
}
}
},
"steps_from_proto": {
"total": 0.2709963110160061,
"count": 198,
"is_parallel": true,
"self": 0.04728555095698539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.22371076005902069,
"count": 792,
"is_parallel": true,
"self": 0.22371076005902069
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 11652.23790770751,
"count": 1361678,
"self": 249.20661963368548,
"children": {
"process_trajectory": {
"total": 4198.827744278771,
"count": 1361678,
"self": 4190.660633005776,
"children": {
"RLTrainer._checkpoint": {
"total": 8.167111272995271,
"count": 40,
"self": 8.167111272995271
}
}
},
"_update_policy": {
"total": 7204.203543795053,
"count": 960,
"self": 5050.691455942814,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2153.5120878522384,
"count": 14400,
"self": 2153.5120878522384
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7510028555989265e-06,
"count": 1,
"self": 1.7510028555989265e-06
},
"TrainerController._save_models": {
"total": 0.2233667710024747,
"count": 1,
"self": 0.001880750001873821,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22148602100060089,
"count": 1,
"self": 0.22148602100060089
}
}
}
}
}
}
}