satcos's picture
First Push
d97f8e0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0279604196548462,
"min": 1.0279604196548462,
"max": 2.8486196994781494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9860.1962890625,
"min": 9860.1962890625,
"max": 29141.37890625,
"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": 11.76163387298584,
"min": 0.3960210382938385,
"max": 11.76163387298584,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2293.5185546875,
"min": 76.82807922363281,
"max": 2381.394287109375,
"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": 0.07125737041282906,
"min": 0.0604676241666882,
"max": 0.07641127008708495,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28502948165131625,
"min": 0.25068665216631236,
"max": 0.35163973144474714,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1958319148158326,
"min": 0.1469772186532032,
"max": 0.2839952024759031,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7833276592633304,
"min": 0.5879088746128128,
"max": 1.4199760123795155,
"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": 23.09090909090909,
"min": 3.772727272727273,
"max": 23.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1016.0,
"min": 166.0,
"max": 1285.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.09090909090909,
"min": 3.772727272727273,
"max": 23.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1016.0,
"min": 166.0,
"max": 1285.0,
"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": "1704966368",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704966835"
},
"total": 467.0211469740002,
"count": 1,
"self": 0.4408398240002498,
"children": {
"run_training.setup": {
"total": 0.045871260000012626,
"count": 1,
"self": 0.045871260000012626
},
"TrainerController.start_learning": {
"total": 466.53443588999994,
"count": 1,
"self": 0.6506830869766418,
"children": {
"TrainerController._reset_env": {
"total": 3.1408191929999703,
"count": 1,
"self": 3.1408191929999703
},
"TrainerController.advance": {
"total": 462.65195178902354,
"count": 18216,
"self": 0.29799204605478735,
"children": {
"env_step": {
"total": 462.35395974296875,
"count": 18216,
"self": 303.3079730409745,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.73897749100456,
"count": 18216,
"self": 1.553016047051642,
"children": {
"TorchPolicy.evaluate": {
"total": 157.18596144395292,
"count": 18216,
"self": 157.18596144395292
}
}
},
"workers": {
"total": 0.3070092109896905,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 465.17023258197287,
"count": 18216,
"is_parallel": true,
"self": 229.0217912209405,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004706626999904984,
"count": 1,
"is_parallel": true,
"self": 0.003436989999954676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012696369999503077,
"count": 10,
"is_parallel": true,
"self": 0.0012696369999503077
}
}
},
"UnityEnvironment.step": {
"total": 0.09192714100004196,
"count": 1,
"is_parallel": true,
"self": 0.0006885679999868444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004602980000072421,
"count": 1,
"is_parallel": true,
"self": 0.0004602980000072421
},
"communicator.exchange": {
"total": 0.08882166200010033,
"count": 1,
"is_parallel": true,
"self": 0.08882166200010033
},
"steps_from_proto": {
"total": 0.001956612999947538,
"count": 1,
"is_parallel": true,
"self": 0.0003664840003239078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00159012899962363,
"count": 10,
"is_parallel": true,
"self": 0.00159012899962363
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.14844136103238,
"count": 18215,
"is_parallel": true,
"self": 11.069145766990232,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.864203779012314,
"count": 18215,
"is_parallel": true,
"self": 5.864203779012314
},
"communicator.exchange": {
"total": 183.9024773090198,
"count": 18215,
"is_parallel": true,
"self": 183.9024773090198
},
"steps_from_proto": {
"total": 35.31261450601005,
"count": 18215,
"is_parallel": true,
"self": 6.731051663981361,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.58156284202869,
"count": 182150,
"is_parallel": true,
"self": 28.58156284202869
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011848099984490545,
"count": 1,
"self": 0.00011848099984490545,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 456.8638691220981,
"count": 702366,
"is_parallel": true,
"self": 14.80474912334057,
"children": {
"process_trajectory": {
"total": 254.45023683875888,
"count": 702366,
"is_parallel": true,
"self": 253.1957712237588,
"children": {
"RLTrainer._checkpoint": {
"total": 1.254465615000072,
"count": 4,
"is_parallel": true,
"self": 1.254465615000072
}
}
},
"_update_policy": {
"total": 187.60888315999864,
"count": 90,
"is_parallel": true,
"self": 55.529730511992284,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.07915264800636,
"count": 4587,
"is_parallel": true,
"self": 132.07915264800636
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09086333999994167,
"count": 1,
"self": 0.0009007180001390225,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08996262199980265,
"count": 1,
"self": 0.08996262199980265
}
}
}
}
}
}
}