Lilyislily's picture
First Push
e051314 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7362285852432251,
"min": 0.7362285852432251,
"max": 2.8618383407592773,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7029.51025390625,
"min": 7029.51025390625,
"max": 29308.0859375,
"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": 12.656803131103516,
"min": 0.3861219584941864,
"max": 12.656803131103516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.07666015625,
"min": 74.90766143798828,
"max": 2578.51953125,
"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": 0.06975477427933548,
"min": 0.06550882781876306,
"max": 0.07452525017770491,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2790190971173419,
"min": 0.26203531127505225,
"max": 0.3726262508885245,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19565641799686,
"min": 0.11354636324012615,
"max": 0.2742633479190808,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.78262567198744,
"min": 0.4541854529605046,
"max": 1.3712914089361825,
"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": 25.068181818181817,
"min": 3.1818181818181817,
"max": 25.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1103.0,
"min": 140.0,
"max": 1361.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.068181818181817,
"min": 3.1818181818181817,
"max": 25.25,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1103.0,
"min": 140.0,
"max": 1361.0,
"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": "1714592414",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714592869"
},
"total": 454.997546757,
"count": 1,
"self": 0.4341611060000332,
"children": {
"run_training.setup": {
"total": 0.0567684930000496,
"count": 1,
"self": 0.0567684930000496
},
"TrainerController.start_learning": {
"total": 454.5066171579999,
"count": 1,
"self": 0.5592534680123435,
"children": {
"TrainerController._reset_env": {
"total": 2.76683517999993,
"count": 1,
"self": 2.76683517999993
},
"TrainerController.advance": {
"total": 451.0860320029876,
"count": 18199,
"self": 0.2735350509873342,
"children": {
"env_step": {
"total": 450.8124969520003,
"count": 18199,
"self": 290.675611861004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.85241462099304,
"count": 18199,
"self": 1.5118270709984927,
"children": {
"TorchPolicy.evaluate": {
"total": 158.34058754999455,
"count": 18199,
"self": 158.34058754999455
}
}
},
"workers": {
"total": 0.28447047000327075,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.3698346710105,
"count": 18199,
"is_parallel": true,
"self": 227.7697750180066,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005709278000040285,
"count": 1,
"is_parallel": true,
"self": 0.0041047019999496115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001604576000090674,
"count": 10,
"is_parallel": true,
"self": 0.001604576000090674
}
}
},
"UnityEnvironment.step": {
"total": 0.03915204999998423,
"count": 1,
"is_parallel": true,
"self": 0.0007028049999462382,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044355499994708225,
"count": 1,
"is_parallel": true,
"self": 0.00044355499994708225
},
"communicator.exchange": {
"total": 0.03573024600007102,
"count": 1,
"is_parallel": true,
"self": 0.03573024600007102
},
"steps_from_proto": {
"total": 0.0022754440000198883,
"count": 1,
"is_parallel": true,
"self": 0.00044228699994164344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018331570000782449,
"count": 10,
"is_parallel": true,
"self": 0.0018331570000782449
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 225.60005965300388,
"count": 18198,
"is_parallel": true,
"self": 10.329293354022411,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4720987689958065,
"count": 18198,
"is_parallel": true,
"self": 5.4720987689958065
},
"communicator.exchange": {
"total": 174.90817225398973,
"count": 18198,
"is_parallel": true,
"self": 174.90817225398973
},
"steps_from_proto": {
"total": 34.89049527599593,
"count": 18198,
"is_parallel": true,
"self": 6.62165800899038,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.26883726700555,
"count": 181980,
"is_parallel": true,
"self": 28.26883726700555
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017658399997344532,
"count": 1,
"self": 0.00017658399997344532,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.20039356796053,
"count": 685292,
"is_parallel": true,
"self": 14.686066205943575,
"children": {
"process_trajectory": {
"total": 246.14276822301667,
"count": 685292,
"is_parallel": true,
"self": 245.55331823601648,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5894499870001937,
"count": 4,
"is_parallel": true,
"self": 0.5894499870001937
}
}
},
"_update_policy": {
"total": 184.37155913900028,
"count": 90,
"is_parallel": true,
"self": 53.87548727600188,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.4960718629984,
"count": 4587,
"is_parallel": true,
"self": 130.4960718629984
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09431992300005732,
"count": 1,
"self": 0.000931018000073891,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09338890499998342,
"count": 1,
"self": 0.09338890499998342
}
}
}
}
}
}
}