dariowsz's picture
First Push
fce79c2
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.95577073097229,
"min": 0.95577073097229,
"max": 2.865797519683838,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9167.7529296875,
"min": 9167.7529296875,
"max": 29380.15625,
"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": 12.667728424072266,
"min": 0.40438613295555115,
"max": 12.667728424072266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2470.20703125,
"min": 78.45091247558594,
"max": 2591.22998046875,
"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": 0.06773849964263397,
"min": 0.063159534162196,
"max": 0.07303339193786801,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27095399857053587,
"min": 0.252638136648784,
"max": 0.3639677955291286,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19992255193053507,
"min": 0.11867737249407334,
"max": 0.30652546758453053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7996902077221403,
"min": 0.47470948997629336,
"max": 1.4103840630428461,
"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": 25.295454545454547,
"min": 3.590909090909091,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 158.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.590909090909091,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 158.0,
"max": 1376.0,
"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": "1690479309",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690479805"
},
"total": 496.206951096,
"count": 1,
"self": 0.8484196929999825,
"children": {
"run_training.setup": {
"total": 0.03616225600001144,
"count": 1,
"self": 0.03616225600001144
},
"TrainerController.start_learning": {
"total": 495.322369147,
"count": 1,
"self": 0.586463293983229,
"children": {
"TrainerController._reset_env": {
"total": 5.000041198999952,
"count": 1,
"self": 5.000041198999952
},
"TrainerController.advance": {
"total": 489.502012398017,
"count": 18217,
"self": 0.28210106001677104,
"children": {
"env_step": {
"total": 489.2199113380002,
"count": 18217,
"self": 354.9071523060056,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.01877672398666,
"count": 18217,
"self": 1.884106445997645,
"children": {
"TorchPolicy.evaluate": {
"total": 132.13467027798902,
"count": 18217,
"self": 132.13467027798902
}
}
},
"workers": {
"total": 0.29398230800791225,
"count": 18217,
"self": 0.0,
"children": {
"worker_root": {
"total": 493.49557944701905,
"count": 18217,
"is_parallel": true,
"self": 233.6806155460191,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005418695999992451,
"count": 1,
"is_parallel": true,
"self": 0.003918713999837564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001499982000154887,
"count": 10,
"is_parallel": true,
"self": 0.001499982000154887
}
}
},
"UnityEnvironment.step": {
"total": 0.04016421900007572,
"count": 1,
"is_parallel": true,
"self": 0.0004411660000869233,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005095760000131122,
"count": 1,
"is_parallel": true,
"self": 0.0005095760000131122
},
"communicator.exchange": {
"total": 0.03698216400005094,
"count": 1,
"is_parallel": true,
"self": 0.03698216400005094
},
"steps_from_proto": {
"total": 0.0022313129999247394,
"count": 1,
"is_parallel": true,
"self": 0.0005160690000138857,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017152439999108537,
"count": 10,
"is_parallel": true,
"self": 0.0017152439999108537
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 259.81496390099994,
"count": 18216,
"is_parallel": true,
"self": 10.899945549976337,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.744042018014284,
"count": 18216,
"is_parallel": true,
"self": 5.744042018014284
},
"communicator.exchange": {
"total": 204.72976243400467,
"count": 18216,
"is_parallel": true,
"self": 204.72976243400467
},
"steps_from_proto": {
"total": 38.44121389900465,
"count": 18216,
"is_parallel": true,
"self": 7.182238766995852,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.2589751320088,
"count": 182160,
"is_parallel": true,
"self": 31.2589751320088
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011229899996578752,
"count": 1,
"self": 0.00011229899996578752,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 485.6157849370343,
"count": 445213,
"is_parallel": true,
"self": 10.703227361040035,
"children": {
"process_trajectory": {
"total": 267.908954470994,
"count": 445213,
"is_parallel": true,
"self": 266.7444910759938,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1644633950002117,
"count": 4,
"is_parallel": true,
"self": 1.1644633950002117
}
}
},
"_update_policy": {
"total": 207.00360310500025,
"count": 90,
"is_parallel": true,
"self": 81.20013923798876,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.80346386701149,
"count": 4587,
"is_parallel": true,
"self": 125.80346386701149
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2337399569998979,
"count": 1,
"self": 0.0011379059999399033,
"children": {
"RLTrainer._checkpoint": {
"total": 0.232602050999958,
"count": 1,
"self": 0.232602050999958
}
}
}
}
}
}
}