ZhihongDeng's picture
First Push
19db9b9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9802771806716919,
"min": 0.9802771806716919,
"max": 2.861733913421631,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9424.384765625,
"min": 9424.384765625,
"max": 29307.017578125,
"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": 12.623039245605469,
"min": 0.34695950150489807,
"max": 12.623039245605469,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2461.49267578125,
"min": 67.31014251708984,
"max": 2540.98291015625,
"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": 0.07073319642279552,
"min": 0.06296938350155246,
"max": 0.07506893241999005,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2829327856911821,
"min": 0.2518775340062098,
"max": 0.3652604016793952,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1919632927313739,
"min": 0.11462330701760948,
"max": 0.2770979132722406,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7678531709254957,
"min": 0.4584932280704379,
"max": 1.342639255574813,
"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": 24.522727272727273,
"min": 3.340909090909091,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1079.0,
"min": 147.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.522727272727273,
"min": 3.340909090909091,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1079.0,
"min": 147.0,
"max": 1391.0,
"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": "1676717604",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676718063"
},
"total": 458.74055159299996,
"count": 1,
"self": 0.3872401999999511,
"children": {
"run_training.setup": {
"total": 0.11133712500003412,
"count": 1,
"self": 0.11133712500003412
},
"TrainerController.start_learning": {
"total": 458.241974268,
"count": 1,
"self": 0.5348831649894805,
"children": {
"TrainerController._reset_env": {
"total": 9.378787008000018,
"count": 1,
"self": 9.378787008000018
},
"TrainerController.advance": {
"total": 448.2092149730104,
"count": 18210,
"self": 0.2758225160082475,
"children": {
"env_step": {
"total": 447.9333924570021,
"count": 18210,
"self": 306.81506629100033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.84687751401185,
"count": 18210,
"self": 1.4795111990073906,
"children": {
"TorchPolicy.evaluate": {
"total": 139.36736631500446,
"count": 18210,
"self": 31.048922904004826,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.31844341099963,
"count": 18210,
"self": 108.31844341099963
}
}
}
}
},
"workers": {
"total": 0.2714486519899424,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.67802764198984,
"count": 18210,
"is_parallel": true,
"self": 221.87418758499166,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009184550999975727,
"count": 1,
"is_parallel": true,
"self": 0.00537438100008103,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003810169999894697,
"count": 10,
"is_parallel": true,
"self": 0.003810169999894697
}
}
},
"UnityEnvironment.step": {
"total": 0.10848053399996616,
"count": 1,
"is_parallel": true,
"self": 0.0007124579999526759,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003823760000045695,
"count": 1,
"is_parallel": true,
"self": 0.0003823760000045695
},
"communicator.exchange": {
"total": 0.09738727500001687,
"count": 1,
"is_parallel": true,
"self": 0.09738727500001687
},
"steps_from_proto": {
"total": 0.00999842499999204,
"count": 1,
"is_parallel": true,
"self": 0.000465477999966879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00953294700002516,
"count": 10,
"is_parallel": true,
"self": 0.00953294700002516
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.80384005699818,
"count": 18209,
"is_parallel": true,
"self": 9.679835052991734,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.262009261011258,
"count": 18209,
"is_parallel": true,
"self": 5.262009261011258
},
"communicator.exchange": {
"total": 188.6450391529968,
"count": 18209,
"is_parallel": true,
"self": 188.6450391529968
},
"steps_from_proto": {
"total": 31.216956589998404,
"count": 18209,
"is_parallel": true,
"self": 6.749554100000978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.467402489997426,
"count": 182090,
"is_parallel": true,
"self": 24.467402489997426
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016195000000607251,
"count": 1,
"self": 0.00016195000000607251,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 444.860205060039,
"count": 404023,
"is_parallel": true,
"self": 10.00412018401579,
"children": {
"process_trajectory": {
"total": 253.74595033002322,
"count": 404023,
"is_parallel": true,
"self": 252.39934686502318,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3466034650000438,
"count": 4,
"is_parallel": true,
"self": 1.3466034650000438
}
}
},
"_update_policy": {
"total": 181.11013454599998,
"count": 90,
"is_parallel": true,
"self": 63.45320164599974,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.65693290000024,
"count": 4584,
"is_parallel": true,
"self": 117.65693290000024
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11892717200009884,
"count": 1,
"self": 0.0008726270000352088,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11805454500006363,
"count": 1,
"self": 0.11805454500006363
}
}
}
}
}
}
}