Holmodi's picture
First Push
80a8e24
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.98992919921875,
"min": 0.98992919921875,
"max": 2.8649089336395264,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9484.51171875,
"min": 9484.51171875,
"max": 29434.07421875,
"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": 12.565169334411621,
"min": 0.38451606035232544,
"max": 12.565169334411621,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2450.2080078125,
"min": 74.59611511230469,
"max": 2563.93359375,
"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": 0.061493387750684345,
"min": 0.061137508690886785,
"max": 0.07281213543660045,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24597355100273738,
"min": 0.24597355100273738,
"max": 0.3640606771830023,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20793091213586282,
"min": 0.11744643133772792,
"max": 0.27284984874959084,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8317236485434513,
"min": 0.4697857253509117,
"max": 1.3642492437479543,
"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": 24.613636363636363,
"min": 3.409090909090909,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1083.0,
"min": 150.0,
"max": 1366.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.613636363636363,
"min": 3.409090909090909,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1083.0,
"min": 150.0,
"max": 1366.0,
"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": "1688009673",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1688010153"
},
"total": 480.3936345939999,
"count": 1,
"self": 0.779740751999725,
"children": {
"run_training.setup": {
"total": 0.04690599300010945,
"count": 1,
"self": 0.04690599300010945
},
"TrainerController.start_learning": {
"total": 479.56698784900004,
"count": 1,
"self": 0.5384461480148275,
"children": {
"TrainerController._reset_env": {
"total": 4.217886713000098,
"count": 1,
"self": 4.217886713000098
},
"TrainerController.advance": {
"total": 474.5931017989851,
"count": 18219,
"self": 0.26287410100530906,
"children": {
"env_step": {
"total": 474.3302276979798,
"count": 18219,
"self": 345.3735640019481,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.69236498800728,
"count": 18219,
"self": 1.7446974129950377,
"children": {
"TorchPolicy.evaluate": {
"total": 126.94766757501225,
"count": 18219,
"self": 126.94766757501225
}
}
},
"workers": {
"total": 0.26429870802439837,
"count": 18219,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.70794676998185,
"count": 18219,
"is_parallel": true,
"self": 224.29260943600684,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006450326000049245,
"count": 1,
"is_parallel": true,
"self": 0.0048363089995291375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001614017000520107,
"count": 10,
"is_parallel": true,
"self": 0.001614017000520107
}
}
},
"UnityEnvironment.step": {
"total": 0.03508439099982752,
"count": 1,
"is_parallel": true,
"self": 0.0005673729997397459,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000418351000007533,
"count": 1,
"is_parallel": true,
"self": 0.000418351000007533
},
"communicator.exchange": {
"total": 0.032009987000037654,
"count": 1,
"is_parallel": true,
"self": 0.032009987000037654
},
"steps_from_proto": {
"total": 0.0020886800000425865,
"count": 1,
"is_parallel": true,
"self": 0.00035902400009035773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017296559999522287,
"count": 10,
"is_parallel": true,
"self": 0.0017296559999522287
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 253.415337333975,
"count": 18218,
"is_parallel": true,
"self": 10.522182478993955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.339373088984985,
"count": 18218,
"is_parallel": true,
"self": 5.339373088984985
},
"communicator.exchange": {
"total": 202.05902505499307,
"count": 18218,
"is_parallel": true,
"self": 202.05902505499307
},
"steps_from_proto": {
"total": 35.49475671100299,
"count": 18218,
"is_parallel": true,
"self": 6.471510443985835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.023246267017157,
"count": 182180,
"is_parallel": true,
"self": 29.023246267017157
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014397700010704284,
"count": 1,
"self": 0.00014397700010704284,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.81345690694457,
"count": 473866,
"is_parallel": true,
"self": 10.227923311874974,
"children": {
"process_trajectory": {
"total": 257.89185765507045,
"count": 473866,
"is_parallel": true,
"self": 256.2750203660705,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6168372889999318,
"count": 4,
"is_parallel": true,
"self": 1.6168372889999318
}
}
},
"_update_policy": {
"total": 202.69367593999914,
"count": 90,
"is_parallel": true,
"self": 77.37003615999151,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.32363978000762,
"count": 4587,
"is_parallel": true,
"self": 125.32363978000762
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21740921199989316,
"count": 1,
"self": 0.0011601419998896745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21624907000000348,
"count": 1,
"self": 0.21624907000000348
}
}
}
}
}
}
}