dcarpintero's picture
First Push
6acf12c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.952407956123352,
"min": 0.952407956123352,
"max": 2.868980646133423,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9125.0205078125,
"min": 9125.0205078125,
"max": 29412.7890625,
"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": 12.853302001953125,
"min": 0.28548750281333923,
"max": 12.853302001953125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2506.393798828125,
"min": 55.38457489013672,
"max": 2612.157958984375,
"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": 0.07049935204279381,
"min": 0.0555507508694313,
"max": 0.07583352228325299,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28199740817117525,
"min": 0.2222030034777252,
"max": 0.379167611416265,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2069701323760491,
"min": 0.1077096020213931,
"max": 0.3309093436920175,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8278805295041964,
"min": 0.4308384080855724,
"max": 1.431545697590884,
"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": 24.931818181818183,
"min": 2.840909090909091,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 125.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 2.840909090909091,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 125.0,
"max": 1396.0,
"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": "1688474618",
"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": "1688475066"
},
"total": 448.529275891,
"count": 1,
"self": 0.44248321599991414,
"children": {
"run_training.setup": {
"total": 0.04325872200001868,
"count": 1,
"self": 0.04325872200001868
},
"TrainerController.start_learning": {
"total": 448.04353395300006,
"count": 1,
"self": 0.503369699999098,
"children": {
"TrainerController._reset_env": {
"total": 5.335307478000004,
"count": 1,
"self": 5.335307478000004
},
"TrainerController.advance": {
"total": 442.06646177100083,
"count": 18203,
"self": 0.23704525798689247,
"children": {
"env_step": {
"total": 441.82941651301394,
"count": 18203,
"self": 323.02365188099566,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.5685777960033,
"count": 18203,
"self": 1.7470305959935786,
"children": {
"TorchPolicy.evaluate": {
"total": 116.82154720000972,
"count": 18203,
"self": 116.82154720000972
}
}
},
"workers": {
"total": 0.2371868360149847,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.65249895701106,
"count": 18203,
"is_parallel": true,
"self": 209.25343061900253,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006325408999941828,
"count": 1,
"is_parallel": true,
"self": 0.004054602999872259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022708060000695696,
"count": 10,
"is_parallel": true,
"self": 0.0022708060000695696
}
}
},
"UnityEnvironment.step": {
"total": 0.03408719399999427,
"count": 1,
"is_parallel": true,
"self": 0.000592099999948914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002481369999713934,
"count": 1,
"is_parallel": true,
"self": 0.0002481369999713934
},
"communicator.exchange": {
"total": 0.03122828400000799,
"count": 1,
"is_parallel": true,
"self": 0.03122828400000799
},
"steps_from_proto": {
"total": 0.0020186730000659736,
"count": 1,
"is_parallel": true,
"self": 0.00035697099997378245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016617020000921912,
"count": 10,
"is_parallel": true,
"self": 0.0016617020000921912
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.39906833800853,
"count": 18202,
"is_parallel": true,
"self": 9.920823417009046,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.05229229999361,
"count": 18202,
"is_parallel": true,
"self": 5.05229229999361
},
"communicator.exchange": {
"total": 189.23489240700485,
"count": 18202,
"is_parallel": true,
"self": 189.23489240700485
},
"steps_from_proto": {
"total": 33.19106021400103,
"count": 18202,
"is_parallel": true,
"self": 5.87669394201896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.314366271982067,
"count": 182020,
"is_parallel": true,
"self": 27.314366271982067
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013585200008492393,
"count": 1,
"self": 0.00013585200008492393,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.7751988809275,
"count": 420378,
"is_parallel": true,
"self": 8.84881431093595,
"children": {
"process_trajectory": {
"total": 240.73103315299124,
"count": 420378,
"is_parallel": true,
"self": 239.59231958399118,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1387135690000605,
"count": 4,
"is_parallel": true,
"self": 1.1387135690000605
}
}
},
"_update_policy": {
"total": 189.19535141700032,
"count": 90,
"is_parallel": true,
"self": 72.16866831200366,
"children": {
"TorchPPOOptimizer.update": {
"total": 117.02668310499666,
"count": 4587,
"is_parallel": true,
"self": 117.02668310499666
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13825915200004602,
"count": 1,
"self": 0.0009125930000664084,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1373465589999796,
"count": 1,
"self": 0.1373465589999796
}
}
}
}
}
}
}