jackoyoungblood's picture
First Push
12e2ec7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.0805633068084717,
"min": 2.0805633068084717,
"max": 2.8661632537841797,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21375.70703125,
"min": 20232.8828125,
"max": 29415.43359375,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 6.874755859375,
"min": 0.24133345484733582,
"max": 6.874755859375,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1402.4501953125,
"min": 46.81869125366211,
"max": 1402.4501953125,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06494636403570207,
"min": 0.0597632026920288,
"max": 0.07687145615142855,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3247318201785104,
"min": 0.24795248164389028,
"max": 0.3562027061804353,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.246456003130651,
"min": 0.11927798000168896,
"max": 0.2882589515956009,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.232280015653255,
"min": 0.47711192000675584,
"max": 1.4085863218003627,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 14.836363636363636,
"min": 3.3181818181818183,
"max": 14.836363636363636,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 816.0,
"min": 146.0,
"max": 816.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 14.836363636363636,
"min": 3.3181818181818183,
"max": 14.836363636363636,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 816.0,
"min": 146.0,
"max": 816.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678213413",
"python_version": "3.8.12 | packaged by conda-forge | (default, Oct 12 2021, 21:59:51) \n[GCC 9.4.0]",
"command_line_arguments": "/opt/conda/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": "1.22.2",
"end_time_seconds": "1678213702"
},
"total": 288.9785879449919,
"count": 1,
"self": 0.42294866777956486,
"children": {
"run_training.setup": {
"total": 0.12219349108636379,
"count": 1,
"self": 0.12219349108636379
},
"TrainerController.start_learning": {
"total": 288.43344578612596,
"count": 1,
"self": 0.3531932751648128,
"children": {
"TrainerController._reset_env": {
"total": 3.69827539101243,
"count": 1,
"self": 3.69827539101243
},
"TrainerController.advance": {
"total": 284.2571554617025,
"count": 9139,
"self": 0.1473305751569569,
"children": {
"env_step": {
"total": 284.10982488654554,
"count": 9139,
"self": 209.80052962130867,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.16032382450067,
"count": 9139,
"self": 0.9090863147284836,
"children": {
"TorchPolicy.evaluate": {
"total": 73.25123750977218,
"count": 9139,
"self": 16.514521210221574,
"children": {
"TorchPolicy.sample_actions": {
"total": 56.73671629955061,
"count": 9139,
"self": 56.73671629955061
}
}
}
}
},
"workers": {
"total": 0.14897144073620439,
"count": 9139,
"self": 0.0,
"children": {
"worker_root": {
"total": 287.8450105616357,
"count": 9139,
"is_parallel": true,
"self": 127.36267962120473,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019215741194784641,
"count": 1,
"is_parallel": true,
"self": 0.0005880279932171106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013335461262613535,
"count": 10,
"is_parallel": true,
"self": 0.0013335461262613535
}
}
},
"UnityEnvironment.step": {
"total": 0.030645938124507666,
"count": 1,
"is_parallel": true,
"self": 0.0003772750496864319,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003385948948562145,
"count": 1,
"is_parallel": true,
"self": 0.0003385948948562145
},
"communicator.exchange": {
"total": 0.028730584075674415,
"count": 1,
"is_parallel": true,
"self": 0.028730584075674415
},
"steps_from_proto": {
"total": 0.0011994841042906046,
"count": 1,
"is_parallel": true,
"self": 0.0002918809186667204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009076031856238842,
"count": 10,
"is_parallel": true,
"self": 0.0009076031856238842
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 160.48233094043098,
"count": 9138,
"is_parallel": true,
"self": 6.340721750166267,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.229251126293093,
"count": 9138,
"is_parallel": true,
"self": 3.229251126293093
},
"communicator.exchange": {
"total": 130.75085783191025,
"count": 9138,
"is_parallel": true,
"self": 130.75085783191025
},
"steps_from_proto": {
"total": 20.16150023206137,
"count": 9138,
"is_parallel": true,
"self": 4.454332082765177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 15.707168149296194,
"count": 91380,
"is_parallel": true,
"self": 15.707168149296194
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00035852217115461826,
"count": 1,
"self": 0.00035852217115461826,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 283.27496223384514,
"count": 126450,
"is_parallel": true,
"self": 3.1808539903722703,
"children": {
"process_trajectory": {
"total": 159.1480010934174,
"count": 126450,
"is_parallel": true,
"self": 158.49808056140319,
"children": {
"RLTrainer._checkpoint": {
"total": 0.649920532014221,
"count": 2,
"is_parallel": true,
"self": 0.649920532014221
}
}
},
"_update_policy": {
"total": 120.94610715005547,
"count": 45,
"is_parallel": true,
"self": 32.3338413417805,
"children": {
"TorchPPOOptimizer.update": {
"total": 88.61226580827497,
"count": 2292,
"is_parallel": true,
"self": 88.61226580827497
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12446313607506454,
"count": 1,
"self": 0.000653072027489543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.123810064047575,
"count": 1,
"self": 0.123810064047575
}
}
}
}
}
}
}