AhmedTarek's picture
First Push
fe0a210 verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9129891991615295,
"min": 0.9129891991615295,
"max": 2.869230270385742,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8727.263671875,
"min": 8727.263671875,
"max": 29415.349609375,
"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": 13.099058151245117,
"min": 0.32880231738090515,
"max": 13.11684799194336,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2554.31640625,
"min": 63.78764724731445,
"max": 2675.8369140625,
"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": 0.06748257392039295,
"min": 0.06239080346302431,
"max": 0.07279959878303321,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2699302956815718,
"min": 0.24956321385209723,
"max": 0.3564335968449265,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18962852240485306,
"min": 0.12020784392313776,
"max": 0.2978825405532239,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7585140896194122,
"min": 0.480831375692551,
"max": 1.4249145131485135,
"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": 25.40909090909091,
"min": 3.3863636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 149.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.3863636363636362,
"max": 25.618181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 149.0,
"max": 1409.0,
"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": "1714837917",
"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": "1714838511"
},
"total": 594.1579342749999,
"count": 1,
"self": 0.7033106989998714,
"children": {
"run_training.setup": {
"total": 0.0898707320000085,
"count": 1,
"self": 0.0898707320000085
},
"TrainerController.start_learning": {
"total": 593.364752844,
"count": 1,
"self": 0.8534971659862549,
"children": {
"TrainerController._reset_env": {
"total": 4.059317118999957,
"count": 1,
"self": 4.059317118999957
},
"TrainerController.advance": {
"total": 588.334647113014,
"count": 18201,
"self": 0.41902320902056545,
"children": {
"env_step": {
"total": 587.9156239039934,
"count": 18201,
"self": 454.54647128497936,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.5215599810091,
"count": 18201,
"self": 2.48596005300692,
"children": {
"TorchPolicy.evaluate": {
"total": 130.03559992800217,
"count": 18201,
"self": 130.03559992800217
}
}
},
"workers": {
"total": 0.8475926380049259,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 591.3756746100031,
"count": 18201,
"is_parallel": true,
"self": 275.67000941399385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011939025999936348,
"count": 1,
"is_parallel": true,
"self": 0.006315710999956536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0056233149999798115,
"count": 10,
"is_parallel": true,
"self": 0.0056233149999798115
}
}
},
"UnityEnvironment.step": {
"total": 0.050747664000027726,
"count": 1,
"is_parallel": true,
"self": 0.0008362439999700655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0007566870000346171,
"count": 1,
"is_parallel": true,
"self": 0.0007566870000346171
},
"communicator.exchange": {
"total": 0.046381114000041634,
"count": 1,
"is_parallel": true,
"self": 0.046381114000041634
},
"steps_from_proto": {
"total": 0.0027736189999814087,
"count": 1,
"is_parallel": true,
"self": 0.000527582000017901,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022460369999635077,
"count": 10,
"is_parallel": true,
"self": 0.0022460369999635077
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 315.70566519600925,
"count": 18200,
"is_parallel": true,
"self": 15.390035720004562,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.924618452996697,
"count": 18200,
"is_parallel": true,
"self": 7.924618452996697
},
"communicator.exchange": {
"total": 247.48744277199648,
"count": 18200,
"is_parallel": true,
"self": 247.48744277199648
},
"steps_from_proto": {
"total": 44.90356825101151,
"count": 18200,
"is_parallel": true,
"self": 9.14424488702889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 35.75932336398262,
"count": 182000,
"is_parallel": true,
"self": 35.75932336398262
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001517559999228979,
"count": 1,
"self": 0.0001517559999228979,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 581.6741393719279,
"count": 746635,
"is_parallel": true,
"self": 17.62313225687126,
"children": {
"process_trajectory": {
"total": 317.5939968780567,
"count": 746635,
"is_parallel": true,
"self": 316.88551817705684,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7084787009998763,
"count": 4,
"is_parallel": true,
"self": 0.7084787009998763
}
}
},
"_update_policy": {
"total": 246.45701023699996,
"count": 90,
"is_parallel": true,
"self": 68.47073964901051,
"children": {
"TorchPPOOptimizer.update": {
"total": 177.98627058798945,
"count": 4587,
"is_parallel": true,
"self": 177.98627058798945
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11713968999993085,
"count": 1,
"self": 0.0017428799999379407,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11539680999999291,
"count": 1,
"self": 0.11539680999999291
}
}
}
}
}
}
}