mjschock's picture
First Push
d263f9f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9217201471328735,
"min": 0.9217201471328735,
"max": 2.8718841075897217,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8800.583984375,
"min": 8800.583984375,
"max": 29410.96484375,
"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": 12.946056365966797,
"min": 0.3159193694591522,
"max": 12.946056365966797,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2524.48095703125,
"min": 61.28835678100586,
"max": 2608.224365234375,
"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": 0.05781570301084738,
"min": 0.05781570301084738,
"max": 0.0753000892137232,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23126281204338953,
"min": 0.23126281204338953,
"max": 0.3747956091207087,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22241900941612675,
"min": 0.12038162856262324,
"max": 0.28058572171949875,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.889676037664507,
"min": 0.481526514250493,
"max": 1.4029286085974937,
"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": 25.704545454545453,
"min": 2.9545454545454546,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 130.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 2.9545454545454546,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 130.0,
"max": 1395.0,
"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": "1675547499",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675548002"
},
"total": 503.09055466200005,
"count": 1,
"self": 0.3893147209998915,
"children": {
"run_training.setup": {
"total": 0.18115532600006645,
"count": 1,
"self": 0.18115532600006645
},
"TrainerController.start_learning": {
"total": 502.5200846150001,
"count": 1,
"self": 0.5814624589885398,
"children": {
"TrainerController._reset_env": {
"total": 10.173636454000075,
"count": 1,
"self": 10.173636454000075
},
"TrainerController.advance": {
"total": 491.6380801340115,
"count": 18202,
"self": 0.3079818750089771,
"children": {
"env_step": {
"total": 491.3300982590025,
"count": 18202,
"self": 340.8338306610053,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.19345422900153,
"count": 18202,
"self": 1.5923598969956174,
"children": {
"TorchPolicy.evaluate": {
"total": 148.6010943320059,
"count": 18202,
"self": 33.290892829994846,
"children": {
"TorchPolicy.sample_actions": {
"total": 115.31020150201107,
"count": 18202,
"self": 115.31020150201107
}
}
}
}
},
"workers": {
"total": 0.3028133689956576,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 500.9552311590038,
"count": 18202,
"is_parallel": true,
"self": 240.5594288320026,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0072496679999858316,
"count": 1,
"is_parallel": true,
"self": 0.00400862099979804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003241047000187791,
"count": 10,
"is_parallel": true,
"self": 0.003241047000187791
}
}
},
"UnityEnvironment.step": {
"total": 0.04871539499993105,
"count": 1,
"is_parallel": true,
"self": 0.0006097099998214617,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027189600007204717,
"count": 1,
"is_parallel": true,
"self": 0.00027189600007204717
},
"communicator.exchange": {
"total": 0.04578341800004182,
"count": 1,
"is_parallel": true,
"self": 0.04578341800004182
},
"steps_from_proto": {
"total": 0.002050370999995721,
"count": 1,
"is_parallel": true,
"self": 0.0004931800001486408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00155719099984708,
"count": 10,
"is_parallel": true,
"self": 0.00155719099984708
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.3958023270012,
"count": 18201,
"is_parallel": true,
"self": 9.124058672994693,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.419393529990771,
"count": 18201,
"is_parallel": true,
"self": 5.419393529990771
},
"communicator.exchange": {
"total": 208.41153709901857,
"count": 18201,
"is_parallel": true,
"self": 208.41153709901857
},
"steps_from_proto": {
"total": 37.44081302499717,
"count": 18201,
"is_parallel": true,
"self": 7.918469334005408,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.52234369099176,
"count": 182010,
"is_parallel": true,
"self": 29.52234369099176
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.371199997876829e-05,
"count": 1,
"self": 4.371199997876829e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 487.8018541929848,
"count": 431092,
"is_parallel": true,
"self": 11.776065052046533,
"children": {
"process_trajectory": {
"total": 278.3211823939382,
"count": 431092,
"is_parallel": true,
"self": 277.54224515093813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7789372430000867,
"count": 4,
"is_parallel": true,
"self": 0.7789372430000867
}
}
},
"_update_policy": {
"total": 197.70460674700007,
"count": 90,
"is_parallel": true,
"self": 70.04708423000136,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.65752251699871,
"count": 4587,
"is_parallel": true,
"self": 127.65752251699871
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.126861856000005,
"count": 1,
"self": 0.0010098660000039672,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12585199000000102,
"count": 1,
"self": 0.12585199000000102
}
}
}
}
}
}
}