Varaprabha's picture
First Push
f46c5b3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9920106530189514,
"min": 0.98935866355896,
"max": 2.864534616470337,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9471.7177734375,
"min": 9471.7177734375,
"max": 29398.71875,
"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": 12.86922836303711,
"min": 0.32066038250923157,
"max": 12.86922836303711,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2509.49951171875,
"min": 62.20811462402344,
"max": 2598.394287109375,
"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": 0.06037384427591129,
"min": 0.06037384427591129,
"max": 0.07257898631345883,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24149537710364516,
"min": 0.24149537710364516,
"max": 0.36203136000846164,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20671778259908452,
"min": 0.1032047217298646,
"max": 0.2772026533662688,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8268711303963381,
"min": 0.4128188869194584,
"max": 1.386013266831344,
"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": 25.181818181818183,
"min": 2.9545454545454546,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 130.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 2.9545454545454546,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 130.0,
"max": 1406.0,
"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": "1686136414",
"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=SnowballTarget4 --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": "1686136857"
},
"total": 442.92654457099997,
"count": 1,
"self": 0.43535280399993326,
"children": {
"run_training.setup": {
"total": 0.04215254799999002,
"count": 1,
"self": 0.04215254799999002
},
"TrainerController.start_learning": {
"total": 442.44903921900004,
"count": 1,
"self": 0.4983787569910305,
"children": {
"TrainerController._reset_env": {
"total": 3.770042851000028,
"count": 1,
"self": 3.770042851000028
},
"TrainerController.advance": {
"total": 438.04807995200895,
"count": 18201,
"self": 0.23328918200394355,
"children": {
"env_step": {
"total": 437.814790770005,
"count": 18201,
"self": 319.396248403009,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.17519855299435,
"count": 18201,
"self": 1.6762655909898285,
"children": {
"TorchPolicy.evaluate": {
"total": 116.49893296200452,
"count": 18201,
"self": 116.49893296200452
}
}
},
"workers": {
"total": 0.24334381400166194,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.9163057910036,
"count": 18201,
"is_parallel": true,
"self": 205.78652704500576,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0049254559999667435,
"count": 1,
"is_parallel": true,
"self": 0.003508238999927471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014172170000392725,
"count": 10,
"is_parallel": true,
"self": 0.0014172170000392725
}
}
},
"UnityEnvironment.step": {
"total": 0.03801949300003571,
"count": 1,
"is_parallel": true,
"self": 0.0006430010000144648,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003420060000394187,
"count": 1,
"is_parallel": true,
"self": 0.0003420060000394187
},
"communicator.exchange": {
"total": 0.03426319099997954,
"count": 1,
"is_parallel": true,
"self": 0.03426319099997954
},
"steps_from_proto": {
"total": 0.002771295000002283,
"count": 1,
"is_parallel": true,
"self": 0.0006056919999650745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021656030000372084,
"count": 10,
"is_parallel": true,
"self": 0.0021656030000372084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.12977874599784,
"count": 18200,
"is_parallel": true,
"self": 9.909842016007701,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.058522917001881,
"count": 18200,
"is_parallel": true,
"self": 5.058522917001881
},
"communicator.exchange": {
"total": 187.61095799700269,
"count": 18200,
"is_parallel": true,
"self": 187.61095799700269
},
"steps_from_proto": {
"total": 32.55045581598557,
"count": 18200,
"is_parallel": true,
"self": 5.856055072979416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.694400743006156,
"count": 182000,
"is_parallel": true,
"self": 26.694400743006156
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010182100004385575,
"count": 1,
"self": 0.00010182100004385575,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.840392688984,
"count": 414683,
"is_parallel": true,
"self": 8.875576174945877,
"children": {
"process_trajectory": {
"total": 238.25985259103828,
"count": 414683,
"is_parallel": true,
"self": 236.94144595003826,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3184066410000241,
"count": 4,
"is_parallel": true,
"self": 1.3184066410000241
}
}
},
"_update_policy": {
"total": 187.70496392299987,
"count": 90,
"is_parallel": true,
"self": 70.25442072599873,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.45054319700114,
"count": 4584,
"is_parallel": true,
"self": 117.45054319700114
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13243583799999215,
"count": 1,
"self": 0.000931655999920622,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13150418200007152,
"count": 1,
"self": 0.13150418200007152
}
}
}
}
}
}
}