fazito25's picture
First Push
355627a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8800565600395203,
"min": 0.8800565600395203,
"max": 2.867924690246582,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8402.7802734375,
"min": 8402.7802734375,
"max": 29370.416015625,
"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": 12.913509368896484,
"min": 0.3893786668777466,
"max": 12.913509368896484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.13427734375,
"min": 75.53945922851562,
"max": 2608.83837890625,
"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": 0.06939926563092169,
"min": 0.06103999921527015,
"max": 0.07205191318940955,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27759706252368677,
"min": 0.2441599968610806,
"max": 0.3602595659470478,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2265521252126086,
"min": 0.12768589727370544,
"max": 0.28748828102560603,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9062085008504344,
"min": 0.5107435890948218,
"max": 1.4374414051280302,
"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": 25.34090909090909,
"min": 3.227272727272727,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 142.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.227272727272727,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 142.0,
"max": 1399.0,
"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": "1708876946",
"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": "1708877371"
},
"total": 425.54391497299997,
"count": 1,
"self": 0.4405962469999736,
"children": {
"run_training.setup": {
"total": 0.0550486879999994,
"count": 1,
"self": 0.0550486879999994
},
"TrainerController.start_learning": {
"total": 425.048270038,
"count": 1,
"self": 0.5302292619935542,
"children": {
"TrainerController._reset_env": {
"total": 3.22413775199999,
"count": 1,
"self": 3.22413775199999
},
"TrainerController.advance": {
"total": 421.2006949680065,
"count": 18199,
"self": 0.2564602950081394,
"children": {
"env_step": {
"total": 420.94423467299833,
"count": 18199,
"self": 269.2375601549889,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.44355788100967,
"count": 18199,
"self": 1.4083097620068088,
"children": {
"TorchPolicy.evaluate": {
"total": 150.03524811900286,
"count": 18199,
"self": 150.03524811900286
}
}
},
"workers": {
"total": 0.2631166369997686,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.99970930399854,
"count": 18199,
"is_parallel": true,
"self": 212.7688531219972,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00501579199999469,
"count": 1,
"is_parallel": true,
"self": 0.003386196999940694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001629595000053996,
"count": 10,
"is_parallel": true,
"self": 0.001629595000053996
}
}
},
"UnityEnvironment.step": {
"total": 0.03592893300003652,
"count": 1,
"is_parallel": true,
"self": 0.0006345180000835171,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004069240000035279,
"count": 1,
"is_parallel": true,
"self": 0.0004069240000035279
},
"communicator.exchange": {
"total": 0.03286634699998103,
"count": 1,
"is_parallel": true,
"self": 0.03286634699998103
},
"steps_from_proto": {
"total": 0.0020211439999684444,
"count": 1,
"is_parallel": true,
"self": 0.0003990459999840823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001622097999984362,
"count": 10,
"is_parallel": true,
"self": 0.001622097999984362
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.23085618200133,
"count": 18198,
"is_parallel": true,
"self": 10.409117955993963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.149796747004359,
"count": 18198,
"is_parallel": true,
"self": 5.149796747004359
},
"communicator.exchange": {
"total": 163.0193326560016,
"count": 18198,
"is_parallel": true,
"self": 163.0193326560016
},
"steps_from_proto": {
"total": 32.6526088230014,
"count": 18198,
"is_parallel": true,
"self": 5.973048813008916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.679560009992485,
"count": 181980,
"is_parallel": true,
"self": 26.679560009992485
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012108900000384892,
"count": 1,
"self": 0.00012108900000384892,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 415.77455075604473,
"count": 655730,
"is_parallel": true,
"self": 13.686115240061952,
"children": {
"process_trajectory": {
"total": 229.26003629498274,
"count": 655730,
"is_parallel": true,
"self": 228.77056217498267,
"children": {
"RLTrainer._checkpoint": {
"total": 0.48947412000006807,
"count": 4,
"is_parallel": true,
"self": 0.48947412000006807
}
}
},
"_update_policy": {
"total": 172.82839922100004,
"count": 90,
"is_parallel": true,
"self": 49.59609828999862,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.23230093100142,
"count": 4587,
"is_parallel": true,
"self": 123.23230093100142
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09308696699997654,
"count": 1,
"self": 0.0009273880000364443,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0921595789999401,
"count": 1,
"self": 0.0921595789999401
}
}
}
}
}
}
}