luhx's picture
First Push
724d84c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7850792407989502,
"min": 0.7850792407989502,
"max": 2.868675470352173,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7495.9365234375,
"min": 7495.9365234375,
"max": 29504.328125,
"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": 12.993101119995117,
"min": 0.5065226554870605,
"max": 12.993101119995117,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.65478515625,
"min": 98.26539611816406,
"max": 2626.34765625,
"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": 0.06957215874760603,
"min": 0.06150973225857004,
"max": 0.07572714875619996,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2782886349904241,
"min": 0.24603892903428015,
"max": 0.36985439890646804,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18354895714597377,
"min": 0.13739150264711283,
"max": 0.2993045777666802,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7341958285838951,
"min": 0.5495660105884513,
"max": 1.496522888833401,
"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": 25.818181818181817,
"min": 3.840909090909091,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1136.0,
"min": 169.0,
"max": 1430.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.818181818181817,
"min": 3.840909090909091,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1136.0,
"min": 169.0,
"max": 1430.0,
"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": "1689136522",
"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": "1689136978"
},
"total": 455.7751864879999,
"count": 1,
"self": 0.4306753100000833,
"children": {
"run_training.setup": {
"total": 0.0425063399999317,
"count": 1,
"self": 0.0425063399999317
},
"TrainerController.start_learning": {
"total": 455.3020048379999,
"count": 1,
"self": 0.500029249999443,
"children": {
"TrainerController._reset_env": {
"total": 4.079659741,
"count": 1,
"self": 4.079659741
},
"TrainerController.advance": {
"total": 450.5838070820006,
"count": 18201,
"self": 0.24991835401544904,
"children": {
"env_step": {
"total": 450.33388872798514,
"count": 18201,
"self": 327.2708346739697,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.80704543701302,
"count": 18201,
"self": 1.7335151500204802,
"children": {
"TorchPolicy.evaluate": {
"total": 121.07353028699254,
"count": 18201,
"self": 121.07353028699254
}
}
},
"workers": {
"total": 0.25600861700240785,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.7617699639959,
"count": 18201,
"is_parallel": true,
"self": 216.87430128998437,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009908701000085784,
"count": 1,
"is_parallel": true,
"self": 0.005075669999996535,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00483303100008925,
"count": 10,
"is_parallel": true,
"self": 0.00483303100008925
}
}
},
"UnityEnvironment.step": {
"total": 0.04414951600006134,
"count": 1,
"is_parallel": true,
"self": 0.00044694600012462615,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031212800001867436,
"count": 1,
"is_parallel": true,
"self": 0.00031212800001867436
},
"communicator.exchange": {
"total": 0.04170043999999962,
"count": 1,
"is_parallel": true,
"self": 0.04170043999999962
},
"steps_from_proto": {
"total": 0.0016900019999184224,
"count": 1,
"is_parallel": true,
"self": 0.00028966499985472183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014003370000637005,
"count": 10,
"is_parallel": true,
"self": 0.0014003370000637005
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 236.88746867401153,
"count": 18200,
"is_parallel": true,
"self": 10.174178087015434,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.102522757998258,
"count": 18200,
"is_parallel": true,
"self": 5.102522757998258
},
"communicator.exchange": {
"total": 187.48246142999528,
"count": 18200,
"is_parallel": true,
"self": 187.48246142999528
},
"steps_from_proto": {
"total": 34.128306399002554,
"count": 18200,
"is_parallel": true,
"self": 5.963698351001767,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.164608048000787,
"count": 182000,
"is_parallel": true,
"self": 28.164608048000787
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011556499998732761,
"count": 1,
"self": 0.00011556499998732761,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.0916291719898,
"count": 431405,
"is_parallel": true,
"self": 9.418847429915786,
"children": {
"process_trajectory": {
"total": 242.7452104750745,
"count": 431405,
"is_parallel": true,
"self": 242.00242183207445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7427886430000399,
"count": 4,
"is_parallel": true,
"self": 0.7427886430000399
}
}
},
"_update_policy": {
"total": 194.9275712669995,
"count": 90,
"is_parallel": true,
"self": 76.72974706799687,
"children": {
"TorchPPOOptimizer.update": {
"total": 118.19782419900264,
"count": 4587,
"is_parallel": true,
"self": 118.19782419900264
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1383931999998822,
"count": 1,
"self": 0.0008773959998507053,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1375158040000315,
"count": 1,
"self": 0.1375158040000315
}
}
}
}
}
}
}