Frorozcol's picture
First Push
a60150a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7719936966896057,
"min": 0.7719936966896057,
"max": 2.8719851970672607,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7370.99609375,
"min": 7370.99609375,
"max": 29412.0,
"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": 13.078685760498047,
"min": 0.19172576069831848,
"max": 13.078685760498047,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2550.34375,
"min": 37.19479751586914,
"max": 2666.04052734375,
"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": 0.07181246412630357,
"min": 0.061381198990377875,
"max": 0.07763386265027758,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2872498565052143,
"min": 0.2573258976004653,
"max": 0.38816931325138787,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.187945421529459,
"min": 0.09724730136461884,
"max": 0.2913610927030152,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.751781686117836,
"min": 0.3889892054584754,
"max": 1.456805463515076,
"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": 25.0,
"min": 2.909090909090909,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 128.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 2.909090909090909,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 128.0,
"max": 1426.0,
"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": "1677784671",
"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": "1.22.4",
"end_time_seconds": "1677785143"
},
"total": 471.539383847,
"count": 1,
"self": 0.4360228749999351,
"children": {
"run_training.setup": {
"total": 0.11743617000001905,
"count": 1,
"self": 0.11743617000001905
},
"TrainerController.start_learning": {
"total": 470.98592480200006,
"count": 1,
"self": 0.5186791110022,
"children": {
"TrainerController._reset_env": {
"total": 8.564480797999977,
"count": 1,
"self": 8.564480797999977
},
"TrainerController.advance": {
"total": 461.78321075699785,
"count": 18203,
"self": 0.2827951589979989,
"children": {
"env_step": {
"total": 461.50041559799985,
"count": 18203,
"self": 318.71742126999396,
"children": {
"SubprocessEnvManager._take_step": {
"total": 142.50616887700414,
"count": 18203,
"self": 1.5076133320142162,
"children": {
"TorchPolicy.evaluate": {
"total": 140.99855554498993,
"count": 18203,
"self": 31.718922299974338,
"children": {
"TorchPolicy.sample_actions": {
"total": 109.27963324501559,
"count": 18203,
"self": 109.27963324501559
}
}
}
}
},
"workers": {
"total": 0.2768254510017414,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 469.5503319709843,
"count": 18203,
"is_parallel": true,
"self": 229.47555947298605,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005451316999995015,
"count": 1,
"is_parallel": true,
"self": 0.004066548999958286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001384768000036729,
"count": 10,
"is_parallel": true,
"self": 0.001384768000036729
}
}
},
"UnityEnvironment.step": {
"total": 0.04757740200000171,
"count": 1,
"is_parallel": true,
"self": 0.00043447799998830305,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032749500002182685,
"count": 1,
"is_parallel": true,
"self": 0.00032749500002182685
},
"communicator.exchange": {
"total": 0.04457409200000484,
"count": 1,
"is_parallel": true,
"self": 0.04457409200000484
},
"steps_from_proto": {
"total": 0.0022413369999867427,
"count": 1,
"is_parallel": true,
"self": 0.0005026640000664884,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017386729999202544,
"count": 10,
"is_parallel": true,
"self": 0.0017386729999202544
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 240.07477249799825,
"count": 18202,
"is_parallel": true,
"self": 9.824910704996967,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.279716017999419,
"count": 18202,
"is_parallel": true,
"self": 5.279716017999419
},
"communicator.exchange": {
"total": 193.57711630500648,
"count": 18202,
"is_parallel": true,
"self": 193.57711630500648
},
"steps_from_proto": {
"total": 31.393029469995383,
"count": 18202,
"is_parallel": true,
"self": 6.8564396839956885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.536589785999695,
"count": 182020,
"is_parallel": true,
"self": 24.536589785999695
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012401000003592344,
"count": 1,
"self": 0.00012401000003592344,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 458.2948994559555,
"count": 415131,
"is_parallel": true,
"self": 10.328092366911221,
"children": {
"process_trajectory": {
"total": 261.536154823044,
"count": 415131,
"is_parallel": true,
"self": 260.78241185304404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.753742969999962,
"count": 4,
"is_parallel": true,
"self": 0.753742969999962
}
}
},
"_update_policy": {
"total": 186.43065226600027,
"count": 90,
"is_parallel": true,
"self": 65.18451791900264,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.24613434699762,
"count": 4587,
"is_parallel": true,
"self": 121.24613434699762
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11943012599999747,
"count": 1,
"self": 0.0008530500000460961,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11857707599995138,
"count": 1,
"self": 0.11857707599995138
}
}
}
}
}
}
}