mingdinghan's picture
First Push
81abba0
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9523308873176575,
"min": 0.9523308873176575,
"max": 2.8602442741394043,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9092.85546875,
"min": 9092.85546875,
"max": 29449.076171875,
"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": 12.789322853088379,
"min": 0.467017263174057,
"max": 12.789322853088379,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.91796875,
"min": 90.60134887695312,
"max": 2583.285400390625,
"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": 0.0685021476086809,
"min": 0.06364345792678126,
"max": 0.07468042222928235,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2740085904347236,
"min": 0.2655239695978868,
"max": 0.37340211114641175,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21369227891167009,
"min": 0.13297259112632853,
"max": 0.28412517976088847,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8547691156466803,
"min": 0.5318903645053141,
"max": 1.4206258988044425,
"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": 25.0,
"min": 3.909090909090909,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 172.0,
"max": 1389.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.909090909090909,
"max": 25.254545454545454,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 172.0,
"max": 1389.0,
"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": "1677337515",
"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=SnowballTarget2 --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": "1.22.4",
"end_time_seconds": "1677337951"
},
"total": 436.08855668,
"count": 1,
"self": 0.42336911400002464,
"children": {
"run_training.setup": {
"total": 0.17323457299994516,
"count": 1,
"self": 0.17323457299994516
},
"TrainerController.start_learning": {
"total": 435.49195299300004,
"count": 1,
"self": 0.5561557970092963,
"children": {
"TrainerController._reset_env": {
"total": 6.8285046000000875,
"count": 1,
"self": 6.8285046000000875
},
"TrainerController.advance": {
"total": 427.9928782019906,
"count": 18203,
"self": 0.25999858598629544,
"children": {
"env_step": {
"total": 427.7328796160043,
"count": 18203,
"self": 294.1931181340117,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.28804681400902,
"count": 18203,
"self": 1.4326998540111617,
"children": {
"TorchPolicy.evaluate": {
"total": 131.85534695999786,
"count": 18203,
"self": 29.293759090988488,
"children": {
"TorchPolicy.sample_actions": {
"total": 102.56158786900937,
"count": 18203,
"self": 102.56158786900937
}
}
}
}
},
"workers": {
"total": 0.251714667983606,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 434.1366631319913,
"count": 18203,
"is_parallel": true,
"self": 208.05527290996656,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029369709998263716,
"count": 1,
"is_parallel": true,
"self": 0.0009303579997776978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020066130000486737,
"count": 10,
"is_parallel": true,
"self": 0.0020066130000486737
}
}
},
"UnityEnvironment.step": {
"total": 0.03315478699983032,
"count": 1,
"is_parallel": true,
"self": 0.0003470899998774257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029672100004063395,
"count": 1,
"is_parallel": true,
"self": 0.00029672100004063395
},
"communicator.exchange": {
"total": 0.031206619999920804,
"count": 1,
"is_parallel": true,
"self": 0.031206619999920804
},
"steps_from_proto": {
"total": 0.0013043559999914578,
"count": 1,
"is_parallel": true,
"self": 0.00036659500005953305,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009377609999319247,
"count": 10,
"is_parallel": true,
"self": 0.0009377609999319247
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.08139022202477,
"count": 18202,
"is_parallel": true,
"self": 9.242362396021235,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.008353830008446,
"count": 18202,
"is_parallel": true,
"self": 5.008353830008446
},
"communicator.exchange": {
"total": 181.8528998619929,
"count": 18202,
"is_parallel": true,
"self": 181.8528998619929
},
"steps_from_proto": {
"total": 29.977774134002175,
"count": 18202,
"is_parallel": true,
"self": 6.345997814977181,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.631776319024993,
"count": 182020,
"is_parallel": true,
"self": 23.631776319024993
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014413500002774526,
"count": 1,
"self": 0.00014413500002774526,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 424.8995411199662,
"count": 384072,
"is_parallel": true,
"self": 9.140129713043734,
"children": {
"process_trajectory": {
"total": 245.79643161292233,
"count": 384072,
"is_parallel": true,
"self": 244.58762299192244,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2088086209998892,
"count": 4,
"is_parallel": true,
"self": 1.2088086209998892
}
}
},
"_update_policy": {
"total": 169.96297979400015,
"count": 90,
"is_parallel": true,
"self": 56.68642589400815,
"children": {
"TorchPPOOptimizer.update": {
"total": 113.276553899992,
"count": 4584,
"is_parallel": true,
"self": 113.276553899992
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11427025900002263,
"count": 1,
"self": 0.0008788420000200858,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11339141700000255,
"count": 1,
"self": 0.11339141700000255
}
}
}
}
}
}
}