joosma's picture
Ver1
7045f2e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8319704532623291,
"min": 0.8319704532623291,
"max": 2.855581760406494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7961.95703125,
"min": 7961.95703125,
"max": 29244.013671875,
"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": 13.088143348693848,
"min": 0.5108755230903625,
"max": 13.088143348693848,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.18798828125,
"min": 99.10984802246094,
"max": 2647.96533203125,
"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": 0.06678547923335881,
"min": 0.06234837531731875,
"max": 0.07329069719160222,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26714191693343525,
"min": 0.2574189367190497,
"max": 0.3655057490751942,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1977911364506273,
"min": 0.15425045665024834,
"max": 0.2721296124598559,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7911645458025092,
"min": 0.6170018266009933,
"max": 1.3403851551168104,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.295454545454547,
"min": 4.25,
"max": 26.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1157.0,
"min": 187.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.295454545454547,
"min": 4.25,
"max": 26.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1157.0,
"min": 187.0,
"max": 1394.0,
"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": "1714946057",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714946737"
},
"total": 680.0590626720001,
"count": 1,
"self": 0.5523693530000173,
"children": {
"run_training.setup": {
"total": 0.08009453900001517,
"count": 1,
"self": 0.08009453900001517
},
"TrainerController.start_learning": {
"total": 679.4265987800001,
"count": 1,
"self": 0.8249724249970996,
"children": {
"TrainerController._reset_env": {
"total": 4.115477315000021,
"count": 1,
"self": 4.115477315000021
},
"TrainerController.advance": {
"total": 674.378396572003,
"count": 18201,
"self": 0.4307965480027178,
"children": {
"env_step": {
"total": 673.9476000240003,
"count": 18201,
"self": 538.4229533630091,
"children": {
"SubprocessEnvManager._take_step": {
"total": 135.11311766899098,
"count": 18201,
"self": 2.3800945819825756,
"children": {
"TorchPolicy.evaluate": {
"total": 132.7330230870084,
"count": 18201,
"self": 132.7330230870084
}
}
},
"workers": {
"total": 0.41152899200017146,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 677.5172543459953,
"count": 18201,
"is_parallel": true,
"self": 365.6508027449979,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00796085399997537,
"count": 1,
"is_parallel": true,
"self": 0.005523409999909745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002437444000065625,
"count": 10,
"is_parallel": true,
"self": 0.002437444000065625
}
}
},
"UnityEnvironment.step": {
"total": 0.04621484099993722,
"count": 1,
"is_parallel": true,
"self": 0.0008173789999545988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005351570000584616,
"count": 1,
"is_parallel": true,
"self": 0.0005351570000584616
},
"communicator.exchange": {
"total": 0.04238146899990625,
"count": 1,
"is_parallel": true,
"self": 0.04238146899990625
},
"steps_from_proto": {
"total": 0.0024808360000179164,
"count": 1,
"is_parallel": true,
"self": 0.0005255070001339845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001955328999883932,
"count": 10,
"is_parallel": true,
"self": 0.001955328999883932
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.8664516009974,
"count": 18200,
"is_parallel": true,
"self": 15.036074392012551,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.638654223977937,
"count": 18200,
"is_parallel": true,
"self": 7.638654223977937
},
"communicator.exchange": {
"total": 244.62578264399667,
"count": 18200,
"is_parallel": true,
"self": 244.62578264399667
},
"steps_from_proto": {
"total": 44.56594034101022,
"count": 18200,
"is_parallel": true,
"self": 8.802129430983655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.763810910026564,
"count": 182000,
"is_parallel": true,
"self": 35.763810910026564
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000250389000029827,
"count": 1,
"self": 0.000250389000029827,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 667.3222930349797,
"count": 809973,
"is_parallel": true,
"self": 18.434386747979147,
"children": {
"process_trajectory": {
"total": 313.44982107500016,
"count": 809973,
"is_parallel": true,
"self": 312.72808045600004,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7217406190001157,
"count": 4,
"is_parallel": true,
"self": 0.7217406190001157
}
}
},
"_update_policy": {
"total": 335.4380852120004,
"count": 90,
"is_parallel": true,
"self": 97.35855321500401,
"children": {
"TorchPPOOptimizer.update": {
"total": 238.07953199699637,
"count": 7645,
"is_parallel": true,
"self": 238.07953199699637
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10750207899991437,
"count": 1,
"self": 0.00138228299988441,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10611979600002996,
"count": 1,
"self": 0.10611979600002996
}
}
}
}
}
}
}