danilyef's picture
First Push
a767bde
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9717625379562378,
"min": 0.9550222158432007,
"max": 2.8704147338867188,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9278.388671875,
"min": 9278.388671875,
"max": 29395.91796875,
"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": 13.311771392822266,
"min": 0.578203558921814,
"max": 13.311771392822266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2595.79541015625,
"min": 112.17149353027344,
"max": 2699.803466796875,
"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": 0.06675379711426406,
"min": 0.05634964984118614,
"max": 0.07601340016251068,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26701518845705624,
"min": 0.22539859936474457,
"max": 0.36302334129148084,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21354055375445125,
"min": 0.13811144826239816,
"max": 0.28996245656527725,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.854162215017805,
"min": 0.5524457930495926,
"max": 1.4498122828263862,
"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": 25.931818181818183,
"min": 3.909090909090909,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 172.0,
"max": 1445.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.909090909090909,
"max": 26.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 172.0,
"max": 1445.0,
"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": "1678728467",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1678728951"
},
"total": 484.29191275499994,
"count": 1,
"self": 0.38551231699995014,
"children": {
"run_training.setup": {
"total": 0.11081275999998752,
"count": 1,
"self": 0.11081275999998752
},
"TrainerController.start_learning": {
"total": 483.795587678,
"count": 1,
"self": 0.5671010269958288,
"children": {
"TrainerController._reset_env": {
"total": 10.69931122700001,
"count": 1,
"self": 10.69931122700001
},
"TrainerController.advance": {
"total": 472.32811818000414,
"count": 18208,
"self": 0.2922903850111993,
"children": {
"env_step": {
"total": 472.03582779499294,
"count": 18208,
"self": 341.31389171698925,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.4443408660042,
"count": 18208,
"self": 2.259177067001417,
"children": {
"TorchPolicy.evaluate": {
"total": 128.1851637990028,
"count": 18208,
"self": 128.1851637990028
}
}
},
"workers": {
"total": 0.27759521199948267,
"count": 18208,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.02938986800575,
"count": 18208,
"is_parallel": true,
"self": 234.89749230000888,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005317269999977725,
"count": 1,
"is_parallel": true,
"self": 0.00375545700001112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015618129999666053,
"count": 10,
"is_parallel": true,
"self": 0.0015618129999666053
}
}
},
"UnityEnvironment.step": {
"total": 0.0471046069999943,
"count": 1,
"is_parallel": true,
"self": 0.0005772780000370403,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003958749999810607,
"count": 1,
"is_parallel": true,
"self": 0.0003958749999810607
},
"communicator.exchange": {
"total": 0.044264034999969226,
"count": 1,
"is_parallel": true,
"self": 0.044264034999969226
},
"steps_from_proto": {
"total": 0.0018674190000069757,
"count": 1,
"is_parallel": true,
"self": 0.0004086239998741803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014587950001327954,
"count": 10,
"is_parallel": true,
"self": 0.0014587950001327954
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.13189756799687,
"count": 18207,
"is_parallel": true,
"self": 9.745585918994948,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.195795777990895,
"count": 18207,
"is_parallel": true,
"self": 5.195795777990895
},
"communicator.exchange": {
"total": 201.02075407800078,
"count": 18207,
"is_parallel": true,
"self": 201.02075407800078
},
"steps_from_proto": {
"total": 31.169761793010252,
"count": 18207,
"is_parallel": true,
"self": 6.300113866995787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.869647926014466,
"count": 182070,
"is_parallel": true,
"self": 24.869647926014466
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013351100005820626,
"count": 1,
"self": 0.00013351100005820626,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.6738790899801,
"count": 429589,
"is_parallel": true,
"self": 10.692317091026098,
"children": {
"process_trajectory": {
"total": 258.701962034954,
"count": 429589,
"is_parallel": true,
"self": 256.24654037695404,
"children": {
"RLTrainer._checkpoint": {
"total": 2.4554216579999775,
"count": 4,
"is_parallel": true,
"self": 2.4554216579999775
}
}
},
"_update_policy": {
"total": 199.279599964,
"count": 90,
"is_parallel": true,
"self": 73.53685133999846,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.74274862400154,
"count": 4584,
"is_parallel": true,
"self": 125.74274862400154
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2009237329999678,
"count": 1,
"self": 0.0025118080000083864,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1984119249999594,
"count": 1,
"self": 0.1984119249999594
}
}
}
}
}
}
}