MohaK's picture
First Push
b5b10c1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0607680082321167,
"min": 1.0532712936401367,
"max": 2.8719539642333984,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10209.892578125,
"min": 10209.892578125,
"max": 29380.08984375,
"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": 12.0185546875,
"min": 0.3667955696582794,
"max": 12.0185546875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2343.6181640625,
"min": 71.15834045410156,
"max": 2394.37060546875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07311599919012224,
"min": 0.05807219781997321,
"max": 0.07668839223239474,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29246399676048895,
"min": 0.23228879127989285,
"max": 0.3834419611619737,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2019239641068613,
"min": 0.12011578342279272,
"max": 0.28556695989533964,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8076958564274452,
"min": 0.4804631336911709,
"max": 1.350942958511558,
"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": 24.0,
"min": 3.2045454545454546,
"max": 24.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1056.0,
"min": 141.0,
"max": 1313.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.0,
"min": 3.2045454545454546,
"max": 24.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1056.0,
"min": 141.0,
"max": 1313.0,
"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": "1697298636",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697299095"
},
"total": 459.50584713800004,
"count": 1,
"self": 0.43080696100003024,
"children": {
"run_training.setup": {
"total": 0.046527317000027324,
"count": 1,
"self": 0.046527317000027324
},
"TrainerController.start_learning": {
"total": 459.02851286,
"count": 1,
"self": 0.6282825769952183,
"children": {
"TrainerController._reset_env": {
"total": 7.275198929999988,
"count": 1,
"self": 7.275198929999988
},
"TrainerController.advance": {
"total": 451.0348645460047,
"count": 18207,
"self": 0.2536673589999623,
"children": {
"env_step": {
"total": 450.78119718700475,
"count": 18207,
"self": 307.71615920099936,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.78481022100345,
"count": 18207,
"self": 1.419554918013887,
"children": {
"TorchPolicy.evaluate": {
"total": 141.36525530298957,
"count": 18207,
"self": 141.36525530298957
}
}
},
"workers": {
"total": 0.28022776500193913,
"count": 18207,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.77934938599486,
"count": 18207,
"is_parallel": true,
"self": 220.04546864898157,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007980985000017427,
"count": 1,
"is_parallel": true,
"self": 0.005791854000051444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021891309999659825,
"count": 10,
"is_parallel": true,
"self": 0.0021891309999659825
}
}
},
"UnityEnvironment.step": {
"total": 0.03557440399998768,
"count": 1,
"is_parallel": true,
"self": 0.0005767129999867393,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032000600003811996,
"count": 1,
"is_parallel": true,
"self": 0.00032000600003811996
},
"communicator.exchange": {
"total": 0.03272946699996737,
"count": 1,
"is_parallel": true,
"self": 0.03272946699996737
},
"steps_from_proto": {
"total": 0.0019482179999954496,
"count": 1,
"is_parallel": true,
"self": 0.000367502000017339,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015807159999781106,
"count": 10,
"is_parallel": true,
"self": 0.0015807159999781106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.7338807370133,
"count": 18206,
"is_parallel": true,
"self": 10.458878528012633,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.293715913994447,
"count": 18206,
"is_parallel": true,
"self": 5.293715913994447
},
"communicator.exchange": {
"total": 188.54372501300986,
"count": 18206,
"is_parallel": true,
"self": 188.54372501300986
},
"steps_from_proto": {
"total": 33.43756128199635,
"count": 18206,
"is_parallel": true,
"self": 6.196387510998022,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.24117377099833,
"count": 182060,
"is_parallel": true,
"self": 27.24117377099833
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015372400002888753,
"count": 1,
"self": 0.00015372400002888753,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.4241823010253,
"count": 464589,
"is_parallel": true,
"self": 9.970812786082888,
"children": {
"process_trajectory": {
"total": 253.27515845294334,
"count": 464589,
"is_parallel": true,
"self": 252.51338304994334,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7617754030000015,
"count": 4,
"is_parallel": true,
"self": 0.7617754030000015
}
}
},
"_update_policy": {
"total": 184.1782110619991,
"count": 90,
"is_parallel": true,
"self": 53.23023868699761,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.94797237500148,
"count": 4587,
"is_parallel": true,
"self": 130.94797237500148
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09001308300003075,
"count": 1,
"self": 0.0008935640000800049,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08911951899995074,
"count": 1,
"self": 0.08911951899995074
}
}
}
}
}
}
}