SafetyMary's picture
inital commit
0b1da8b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9847045540809631,
"min": 0.9847045540809631,
"max": 2.8657331466674805,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9412.791015625,
"min": 9412.791015625,
"max": 29379.49609375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.009140014648438,
"min": 0.5156852602958679,
"max": 13.009140014648438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.7822265625,
"min": 100.0429458618164,
"max": 2624.916015625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06962136059005655,
"min": 0.06338916624284621,
"max": 0.07804255028524637,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2784854423602262,
"min": 0.25492094662103243,
"max": 0.39021275142623185,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19730948897845607,
"min": 0.12285670037860708,
"max": 0.28159842490054227,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7892379559138243,
"min": 0.4914268015144283,
"max": 1.4079921245027114,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.90909090909091,
"min": 3.6136363636363638,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1140.0,
"min": 159.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.90909090909091,
"min": 3.6136363636363638,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1140.0,
"min": 159.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1694572381",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1694572889"
},
"total": 508.018515642,
"count": 1,
"self": 0.42801155400002244,
"children": {
"run_training.setup": {
"total": 0.048313414999938686,
"count": 1,
"self": 0.048313414999938686
},
"TrainerController.start_learning": {
"total": 507.54219067300005,
"count": 1,
"self": 0.5913637590027747,
"children": {
"TrainerController._reset_env": {
"total": 4.613010170999928,
"count": 1,
"self": 4.613010170999928
},
"TrainerController.advance": {
"total": 502.18385387599733,
"count": 18202,
"self": 0.29581199299411765,
"children": {
"env_step": {
"total": 501.8880418830032,
"count": 18202,
"self": 363.75494601899595,
"children": {
"SubprocessEnvManager._take_step": {
"total": 137.82834810800546,
"count": 18202,
"self": 1.8024513690000958,
"children": {
"TorchPolicy.evaluate": {
"total": 136.02589673900536,
"count": 18202,
"self": 136.02589673900536
}
}
},
"workers": {
"total": 0.3047477560018024,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 505.9474951289984,
"count": 18202,
"is_parallel": true,
"self": 238.5046865640045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005488755999977002,
"count": 1,
"is_parallel": true,
"self": 0.003911696000272968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015770599997040335,
"count": 10,
"is_parallel": true,
"self": 0.0015770599997040335
}
}
},
"UnityEnvironment.step": {
"total": 0.07509873499998321,
"count": 1,
"is_parallel": true,
"self": 0.000711937999994916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004600170000230719,
"count": 1,
"is_parallel": true,
"self": 0.0004600170000230719
},
"communicator.exchange": {
"total": 0.07058315500000845,
"count": 1,
"is_parallel": true,
"self": 0.07058315500000845
},
"steps_from_proto": {
"total": 0.0033436249999567735,
"count": 1,
"is_parallel": true,
"self": 0.0013279470000497895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002015677999906984,
"count": 10,
"is_parallel": true,
"self": 0.002015677999906984
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 267.4428085649939,
"count": 18201,
"is_parallel": true,
"self": 11.16767970700812,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.950092613003676,
"count": 18201,
"is_parallel": true,
"self": 5.950092613003676
},
"communicator.exchange": {
"total": 209.4596430859948,
"count": 18201,
"is_parallel": true,
"self": 209.4596430859948
},
"steps_from_proto": {
"total": 40.86539315898733,
"count": 18201,
"is_parallel": true,
"self": 7.581187884936867,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.284205274050464,
"count": 182010,
"is_parallel": true,
"self": 33.284205274050464
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012416200002007827,
"count": 1,
"self": 0.00012416200002007827,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 498.0443941960443,
"count": 458734,
"is_parallel": true,
"self": 10.886279963026368,
"children": {
"process_trajectory": {
"total": 273.5628654260181,
"count": 458734,
"is_parallel": true,
"self": 271.09739676801803,
"children": {
"RLTrainer._checkpoint": {
"total": 2.465468658000077,
"count": 4,
"is_parallel": true,
"self": 2.465468658000077
}
}
},
"_update_policy": {
"total": 213.59524880699985,
"count": 90,
"is_parallel": true,
"self": 82.96549107499538,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.62975773200446,
"count": 4581,
"is_parallel": true,
"self": 130.62975773200446
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1538387049999983,
"count": 1,
"self": 0.00108670899999197,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15275199600000633,
"count": 1,
"self": 0.15275199600000633
}
}
}
}
}
}
}