hussamalafandi's picture
First training of SnowballTarget
5376e9f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0047873258590698,
"min": 1.0012943744659424,
"max": 2.8713014125823975,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9637.919921875,
"min": 9637.919921875,
"max": 29499.75,
"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": 12.939949035644531,
"min": 0.3516290485858917,
"max": 12.939949035644531,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2523.2900390625,
"min": 68.21603393554688,
"max": 2635.736572265625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06372350326120226,
"min": 0.06198706673338379,
"max": 0.07246351754906309,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.254894013044809,
"min": 0.254894013044809,
"max": 0.3510581679803698,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20468394275681648,
"min": 0.10045391662324797,
"max": 0.2925594187542504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8187357710272659,
"min": 0.4018156664929919,
"max": 1.3774128042015374,
"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": 25.272727272727273,
"min": 2.8636363636363638,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 126.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 2.8636363636363638,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 126.0,
"max": 1386.0,
"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": "1681062871",
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]",
"command_line_arguments": "/home/hussam/miniconda3/envs/hf-course/bin/mlagents-learn ./ml-agents/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": "1681063190"
},
"total": 318.5286350999959,
"count": 1,
"self": 0.2743779869924765,
"children": {
"run_training.setup": {
"total": 0.08256180500029586,
"count": 1,
"self": 0.08256180500029586
},
"TrainerController.start_learning": {
"total": 318.1716953080031,
"count": 1,
"self": 0.4779832176936907,
"children": {
"TrainerController._reset_env": {
"total": 5.167581194997183,
"count": 1,
"self": 5.167581194997183
},
"TrainerController.advance": {
"total": 312.4212868823088,
"count": 18205,
"self": 0.2281630123470677,
"children": {
"env_step": {
"total": 312.1931238699617,
"count": 18205,
"self": 233.38227509827993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.58142461179523,
"count": 18205,
"self": 1.2021607006026898,
"children": {
"TorchPolicy.evaluate": {
"total": 77.37926391119254,
"count": 18205,
"self": 77.37926391119254
}
}
},
"workers": {
"total": 0.2294241598865483,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 317.63610826191143,
"count": 18205,
"is_parallel": true,
"self": 153.91726262994052,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00159756799985189,
"count": 1,
"is_parallel": true,
"self": 0.0006542549963342026,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009433130035176873,
"count": 10,
"is_parallel": true,
"self": 0.0009433130035176873
}
}
},
"UnityEnvironment.step": {
"total": 0.020083210998564027,
"count": 1,
"is_parallel": true,
"self": 0.0002346299952478148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003603410004870966,
"count": 1,
"is_parallel": true,
"self": 0.0003603410004870966
},
"communicator.exchange": {
"total": 0.01868760400247993,
"count": 1,
"is_parallel": true,
"self": 0.01868760400247993
},
"steps_from_proto": {
"total": 0.0008006360003491864,
"count": 1,
"is_parallel": true,
"self": 0.00018705498951021582,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006135810108389705,
"count": 10,
"is_parallel": true,
"self": 0.0006135810108389705
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 163.7188456319709,
"count": 18204,
"is_parallel": true,
"self": 7.3658151937052025,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.5169708654502756,
"count": 18204,
"is_parallel": true,
"self": 3.5169708654502756
},
"communicator.exchange": {
"total": 129.69160871417262,
"count": 18204,
"is_parallel": true,
"self": 129.69160871417262
},
"steps_from_proto": {
"total": 23.144450858642813,
"count": 18204,
"is_parallel": true,
"self": 4.1889689101226395,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.955481948520173,
"count": 182040,
"is_parallel": true,
"self": 18.955481948520173
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.693999941693619e-05,
"count": 1,
"self": 7.693999941693619e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 311.85909340267244,
"count": 180919,
"is_parallel": true,
"self": 2.561864732968388,
"children": {
"process_trajectory": {
"total": 176.37631771069573,
"count": 180919,
"is_parallel": true,
"self": 175.49994932469417,
"children": {
"RLTrainer._checkpoint": {
"total": 0.876368386001559,
"count": 4,
"is_parallel": true,
"self": 0.876368386001559
}
}
},
"_update_policy": {
"total": 132.92091095900832,
"count": 90,
"is_parallel": true,
"self": 34.498783994218684,
"children": {
"TorchPPOOptimizer.update": {
"total": 98.42212696478964,
"count": 4587,
"is_parallel": true,
"self": 98.42212696478964
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10476707300404087,
"count": 1,
"self": 0.00084700600564247,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1039200669983984,
"count": 1,
"self": 0.1039200669983984
}
}
}
}
}
}
}