Pongsaky's picture
First Push
7c86287
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0906059741973877,
"min": 1.0906059741973877,
"max": 2.8583920001983643,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10425.1025390625,
"min": 10425.1025390625,
"max": 29272.79296875,
"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": 12.215192794799805,
"min": 0.40698009729385376,
"max": 12.215192794799805,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2381.962646484375,
"min": 78.95413970947266,
"max": 2434.2626953125,
"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": 0.06400436742228967,
"min": 0.061178902620974675,
"max": 0.07563608846303038,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25601746968915867,
"min": 0.25601746968915867,
"max": 0.3781804423151519,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2045163095143496,
"min": 0.11820495127604397,
"max": 0.28227418105976254,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8180652380573984,
"min": 0.47281980510417587,
"max": 1.4113709052988126,
"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": 24.25,
"min": 3.4318181818181817,
"max": 24.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1067.0,
"min": 151.0,
"max": 1344.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.25,
"min": 3.4318181818181817,
"max": 24.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1067.0,
"min": 151.0,
"max": 1344.0,
"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": "1703512768",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703513182"
},
"total": 414.757328946,
"count": 1,
"self": 0.43813500400000294,
"children": {
"run_training.setup": {
"total": 0.05311312099996712,
"count": 1,
"self": 0.05311312099996712
},
"TrainerController.start_learning": {
"total": 414.266080821,
"count": 1,
"self": 0.7216988739923522,
"children": {
"TrainerController._reset_env": {
"total": 2.7990162369999894,
"count": 1,
"self": 2.7990162369999894
},
"TrainerController.advance": {
"total": 410.6854990870077,
"count": 18200,
"self": 0.35208162801143317,
"children": {
"env_step": {
"total": 410.3334174589963,
"count": 18200,
"self": 313.2193697469952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.7807271260026,
"count": 18200,
"self": 1.522344449005061,
"children": {
"TorchPolicy.evaluate": {
"total": 95.25838267699754,
"count": 18200,
"self": 95.25838267699754
}
}
},
"workers": {
"total": 0.3333205859984787,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 412.9938453379959,
"count": 18200,
"is_parallel": true,
"self": 182.33384228198497,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0059106749999955355,
"count": 1,
"is_parallel": true,
"self": 0.004284305999988192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016263690000073439,
"count": 10,
"is_parallel": true,
"self": 0.0016263690000073439
}
}
},
"UnityEnvironment.step": {
"total": 0.03567871699999614,
"count": 1,
"is_parallel": true,
"self": 0.0005619389999651503,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041209900001604183,
"count": 1,
"is_parallel": true,
"self": 0.00041209900001604183
},
"communicator.exchange": {
"total": 0.03305369000003111,
"count": 1,
"is_parallel": true,
"self": 0.03305369000003111
},
"steps_from_proto": {
"total": 0.0016509889999838379,
"count": 1,
"is_parallel": true,
"self": 0.0003525600000102713,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012984289999735665,
"count": 10,
"is_parallel": true,
"self": 0.0012984289999735665
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.6600030560109,
"count": 18199,
"is_parallel": true,
"self": 10.65974189400248,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.994297457000073,
"count": 18199,
"is_parallel": true,
"self": 5.994297457000073
},
"communicator.exchange": {
"total": 182.04553671200313,
"count": 18199,
"is_parallel": true,
"self": 182.04553671200313
},
"steps_from_proto": {
"total": 31.96042699300523,
"count": 18199,
"is_parallel": true,
"self": 6.421406608034147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.53902038497108,
"count": 181990,
"is_parallel": true,
"self": 25.53902038497108
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.5410999948435347e-05,
"count": 1,
"self": 5.5410999948435347e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 405.7453876860299,
"count": 661517,
"is_parallel": true,
"self": 12.253253235043246,
"children": {
"process_trajectory": {
"total": 229.67058418598646,
"count": 661517,
"is_parallel": true,
"self": 229.29813382598655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3724503599999025,
"count": 4,
"is_parallel": true,
"self": 0.3724503599999025
}
}
},
"_update_policy": {
"total": 163.8215502650002,
"count": 90,
"is_parallel": true,
"self": 39.59163990999559,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.22991035500462,
"count": 4584,
"is_parallel": true,
"self": 124.22991035500462
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.059811211999999614,
"count": 1,
"self": 0.0007484310000336336,
"children": {
"RLTrainer._checkpoint": {
"total": 0.05906278099996598,
"count": 1,
"self": 0.05906278099996598
}
}
}
}
}
}
}