Yanrds's picture
Init
f0591aa
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.995136022567749,
"min": 0.995136022567749,
"max": 2.8646280765533447,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9589.130859375,
"min": 9589.130859375,
"max": 29399.677734375,
"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": 12.632987976074219,
"min": 0.4650934040546417,
"max": 12.632987976074219,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2463.4326171875,
"min": 90.22811889648438,
"max": 2565.41650390625,
"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": 0.06713069301936318,
"min": 0.061769809126488724,
"max": 0.07602220593664029,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26852277207745273,
"min": 0.2470792365059549,
"max": 0.38011102968320143,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20610196326001018,
"min": 0.12489669911641006,
"max": 0.27721001054434213,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8244078530400407,
"min": 0.49958679646564025,
"max": 1.3597690097841562,
"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": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1365.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.204545454545453,
"min": 3.340909090909091,
"max": 25.204545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1109.0,
"min": 147.0,
"max": 1365.0,
"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": "1681844920",
"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": "1681845403"
},
"total": 482.89332208,
"count": 1,
"self": 0.86070995700004,
"children": {
"run_training.setup": {
"total": 0.10643008800002463,
"count": 1,
"self": 0.10643008800002463
},
"TrainerController.start_learning": {
"total": 481.92618203499995,
"count": 1,
"self": 0.6440070420007942,
"children": {
"TrainerController._reset_env": {
"total": 3.7410844189999466,
"count": 1,
"self": 3.7410844189999466
},
"TrainerController.advance": {
"total": 477.32843284499927,
"count": 18229,
"self": 0.3083740819954528,
"children": {
"env_step": {
"total": 477.0200587630038,
"count": 18229,
"self": 348.50608322500864,
"children": {
"SubprocessEnvManager._take_step": {
"total": 128.21059547199843,
"count": 18229,
"self": 1.8783670219974056,
"children": {
"TorchPolicy.evaluate": {
"total": 126.33222845000103,
"count": 18229,
"self": 126.33222845000103
}
}
},
"workers": {
"total": 0.30338006599674827,
"count": 18229,
"self": 0.0,
"children": {
"worker_root": {
"total": 480.00679483200025,
"count": 18229,
"is_parallel": true,
"self": 219.5033019050041,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00497145700001056,
"count": 1,
"is_parallel": true,
"self": 0.0034401410001123622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015313159998981973,
"count": 10,
"is_parallel": true,
"self": 0.0015313159998981973
}
}
},
"UnityEnvironment.step": {
"total": 0.03513313000001972,
"count": 1,
"is_parallel": true,
"self": 0.0005710039999939909,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003298629999903824,
"count": 1,
"is_parallel": true,
"self": 0.0003298629999903824
},
"communicator.exchange": {
"total": 0.03231383199999982,
"count": 1,
"is_parallel": true,
"self": 0.03231383199999982
},
"steps_from_proto": {
"total": 0.0019184310000355254,
"count": 1,
"is_parallel": true,
"self": 0.0003635570000710686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015548739999644567,
"count": 10,
"is_parallel": true,
"self": 0.0015548739999644567
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 260.50349292699616,
"count": 18228,
"is_parallel": true,
"self": 10.35503890099443,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.78758991699749,
"count": 18228,
"is_parallel": true,
"self": 5.78758991699749
},
"communicator.exchange": {
"total": 209.99492946600958,
"count": 18228,
"is_parallel": true,
"self": 209.99492946600958
},
"steps_from_proto": {
"total": 34.36593464299466,
"count": 18228,
"is_parallel": true,
"self": 6.95249178502678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.41344285796788,
"count": 182280,
"is_parallel": true,
"self": 27.41344285796788
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018330499995045102,
"count": 1,
"self": 0.00018330499995045102,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 473.5715938120172,
"count": 436615,
"is_parallel": true,
"self": 11.001399825009457,
"children": {
"process_trajectory": {
"total": 264.25983589900744,
"count": 436615,
"is_parallel": true,
"self": 262.97724628000736,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2825896190000776,
"count": 4,
"is_parallel": true,
"self": 1.2825896190000776
}
}
},
"_update_policy": {
"total": 198.31035808800033,
"count": 90,
"is_parallel": true,
"self": 72.35241610299914,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.95794198500118,
"count": 4587,
"is_parallel": true,
"self": 125.95794198500118
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21247442399999272,
"count": 1,
"self": 0.0013289309999890975,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21114549300000363,
"count": 1,
"self": 0.21114549300000363
}
}
}
}
}
}
}