gaokaobishuati's picture
First Push
48e28bb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0190352201461792,
"min": 1.0190352201461792,
"max": 2.8657336235046387,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9729.748046875,
"min": 9729.748046875,
"max": 29411.0234375,
"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": 12.449531555175781,
"min": 0.4058632254600525,
"max": 12.449531555175781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2427.65869140625,
"min": 78.73746490478516,
"max": 2505.03466796875,
"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": 0.07088019261398443,
"min": 0.060942872152001795,
"max": 0.07463231801639444,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2835207704559377,
"min": 0.25684822777054483,
"max": 0.3624955352199465,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21335752841596511,
"min": 0.12388089370877281,
"max": 0.2877664540328232,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8534301136638605,
"min": 0.49552357483509124,
"max": 1.4388322701641159,
"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": 24.431818181818183,
"min": 3.7954545454545454,
"max": 24.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1075.0,
"min": 167.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.431818181818183,
"min": 3.7954545454545454,
"max": 24.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1075.0,
"min": 167.0,
"max": 1342.0,
"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": "1683463373",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683463833"
},
"total": 460.3801828080001,
"count": 1,
"self": 0.42421196499992675,
"children": {
"run_training.setup": {
"total": 0.04051842400008354,
"count": 1,
"self": 0.04051842400008354
},
"TrainerController.start_learning": {
"total": 459.9154524190001,
"count": 1,
"self": 0.5343262999984972,
"children": {
"TrainerController._reset_env": {
"total": 5.01344627200001,
"count": 1,
"self": 5.01344627200001
},
"TrainerController.advance": {
"total": 454.2342329450015,
"count": 18201,
"self": 0.2607629510065408,
"children": {
"env_step": {
"total": 453.97346999399497,
"count": 18201,
"self": 331.7973534260127,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.91485877999514,
"count": 18201,
"self": 1.8980169640085478,
"children": {
"TorchPolicy.evaluate": {
"total": 120.0168418159866,
"count": 18201,
"self": 120.0168418159866
}
}
},
"workers": {
"total": 0.2612577879871196,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.3812684169865,
"count": 18201,
"is_parallel": true,
"self": 211.84402884498002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028885489999765923,
"count": 1,
"is_parallel": true,
"self": 0.0006821019999279088,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022064470000486835,
"count": 10,
"is_parallel": true,
"self": 0.0022064470000486835
}
}
},
"UnityEnvironment.step": {
"total": 0.044142435000026126,
"count": 1,
"is_parallel": true,
"self": 0.0006114940000543356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003298089999361764,
"count": 1,
"is_parallel": true,
"self": 0.0003298089999361764
},
"communicator.exchange": {
"total": 0.041330062000042744,
"count": 1,
"is_parallel": true,
"self": 0.041330062000042744
},
"steps_from_proto": {
"total": 0.0018710699999928693,
"count": 1,
"is_parallel": true,
"self": 0.00035850699975981115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015125630002330581,
"count": 10,
"is_parallel": true,
"self": 0.0015125630002330581
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 246.53723957200646,
"count": 18200,
"is_parallel": true,
"self": 9.56935821901277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.13935303198798,
"count": 18200,
"is_parallel": true,
"self": 5.13935303198798
},
"communicator.exchange": {
"total": 199.59378860700315,
"count": 18200,
"is_parallel": true,
"self": 199.59378860700315
},
"steps_from_proto": {
"total": 32.23473971400256,
"count": 18200,
"is_parallel": true,
"self": 6.126801202972388,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.10793851103017,
"count": 182000,
"is_parallel": true,
"self": 26.10793851103017
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012535099995147903,
"count": 1,
"self": 0.00012535099995147903,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.86558287803257,
"count": 423468,
"is_parallel": true,
"self": 9.248122289044545,
"children": {
"process_trajectory": {
"total": 247.49720566798703,
"count": 423468,
"is_parallel": true,
"self": 246.74103058198705,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7561750859999847,
"count": 4,
"is_parallel": true,
"self": 0.7561750859999847
}
}
},
"_update_policy": {
"total": 194.120254921001,
"count": 90,
"is_parallel": true,
"self": 73.8885058340095,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.2317490869915,
"count": 4587,
"is_parallel": true,
"self": 120.2317490869915
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13332155100010823,
"count": 1,
"self": 0.0008920250002120156,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1324295259998962,
"count": 1,
"self": 0.1324295259998962
}
}
}
}
}
}
}