Flooow's picture
First Push
3bd1642
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0453623533248901,
"min": 1.0453623533248901,
"max": 2.8609447479248047,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10015.6171875,
"min": 10015.6171875,
"max": 29361.876953125,
"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": 12.770030975341797,
"min": 0.4463188648223877,
"max": 12.772063255310059,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2490.156005859375,
"min": 86.58586120605469,
"max": 2605.5009765625,
"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": 0.06604274040699809,
"min": 0.057445521787432126,
"max": 0.07883340509565018,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26417096162799236,
"min": 0.2297820871497285,
"max": 0.3784509672618964,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18686193067069146,
"min": 0.10658104606908655,
"max": 0.2726815845452103,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7474477226827658,
"min": 0.4263241842763462,
"max": 1.3247781296571095,
"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": 25.204545454545453,
"min": 3.3181818181818183,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 146.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.3181818181818183,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 146.0,
"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": "1682365084",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682365569"
},
"total": 484.05375823099996,
"count": 1,
"self": 0.39447673599988775,
"children": {
"run_training.setup": {
"total": 0.11807232600006046,
"count": 1,
"self": 0.11807232600006046
},
"TrainerController.start_learning": {
"total": 483.541209169,
"count": 1,
"self": 0.6027911349963233,
"children": {
"TrainerController._reset_env": {
"total": 4.067012671000043,
"count": 1,
"self": 4.067012671000043
},
"TrainerController.advance": {
"total": 478.7322733970037,
"count": 18216,
"self": 0.31659207600375794,
"children": {
"env_step": {
"total": 478.41568132099997,
"count": 18216,
"self": 349.2820805519858,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.84129174600605,
"count": 18216,
"self": 1.980924820002997,
"children": {
"TorchPolicy.evaluate": {
"total": 126.86036692600305,
"count": 18216,
"self": 126.86036692600305
}
}
},
"workers": {
"total": 0.2923090230081016,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 481.84694199899457,
"count": 18216,
"is_parallel": true,
"self": 222.81938307599808,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0052440630000774036,
"count": 1,
"is_parallel": true,
"self": 0.003553857000042626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016902060000347774,
"count": 10,
"is_parallel": true,
"self": 0.0016902060000347774
}
}
},
"UnityEnvironment.step": {
"total": 0.11087387699990359,
"count": 1,
"is_parallel": true,
"self": 0.0005509719998144647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044867700000850164,
"count": 1,
"is_parallel": true,
"self": 0.00044867700000850164
},
"communicator.exchange": {
"total": 0.10766649900006087,
"count": 1,
"is_parallel": true,
"self": 0.10766649900006087
},
"steps_from_proto": {
"total": 0.0022077290000197536,
"count": 1,
"is_parallel": true,
"self": 0.0004158289999622866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001791900000057467,
"count": 10,
"is_parallel": true,
"self": 0.001791900000057467
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 259.0275589229965,
"count": 18215,
"is_parallel": true,
"self": 10.381977617998018,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.8293331269961755,
"count": 18215,
"is_parallel": true,
"self": 5.8293331269961755
},
"communicator.exchange": {
"total": 208.52746064699556,
"count": 18215,
"is_parallel": true,
"self": 208.52746064699556
},
"steps_from_proto": {
"total": 34.28878753100673,
"count": 18215,
"is_parallel": true,
"self": 6.919519764012989,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.369267766993744,
"count": 182150,
"is_parallel": true,
"self": 27.369267766993744
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016025100001115788,
"count": 1,
"self": 0.00016025100001115788,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 474.8834939539755,
"count": 438149,
"is_parallel": true,
"self": 10.930339113977766,
"children": {
"process_trajectory": {
"total": 264.2065188949987,
"count": 438149,
"is_parallel": true,
"self": 263.08546175999857,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1210571350001146,
"count": 4,
"is_parallel": true,
"self": 1.1210571350001146
}
}
},
"_update_policy": {
"total": 199.74663594499907,
"count": 90,
"is_parallel": true,
"self": 73.25947545700137,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.4871604879977,
"count": 4587,
"is_parallel": true,
"self": 126.4871604879977
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13897171499991146,
"count": 1,
"self": 0.0009542679998730819,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13801744700003837,
"count": 1,
"self": 0.13801744700003837
}
}
}
}
}
}
}