Gabcsor's picture
First Push
f559f2b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9685996770858765,
"min": 0.9685996770858765,
"max": 2.8611972332000732,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9248.189453125,
"min": 9248.189453125,
"max": 29301.521484375,
"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": 12.8291015625,
"min": 0.462934672832489,
"max": 12.8291015625,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.6748046875,
"min": 89.809326171875,
"max": 2587.730712890625,
"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": 0.07733338526789642,
"min": 0.06170114920685449,
"max": 0.07733338526789642,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30933354107158567,
"min": 0.24680459682741795,
"max": 0.35925496277495234,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21151370051152565,
"min": 0.1262354629694064,
"max": 0.27168470550985896,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8460548020461026,
"min": 0.5049418518776256,
"max": 1.3584235275492949,
"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": 25.636363636363637,
"min": 3.727272727272727,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 164.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.727272727272727,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 164.0,
"max": 1392.0,
"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": "1678217845",
"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": "1.22.4",
"end_time_seconds": "1678218330"
},
"total": 484.79233795,
"count": 1,
"self": 0.4348106039999493,
"children": {
"run_training.setup": {
"total": 0.18392591200000652,
"count": 1,
"self": 0.18392591200000652
},
"TrainerController.start_learning": {
"total": 484.17360143400003,
"count": 1,
"self": 0.6455502739988219,
"children": {
"TrainerController._reset_env": {
"total": 9.499347833000002,
"count": 1,
"self": 9.499347833000002
},
"TrainerController.advance": {
"total": 473.9070633340013,
"count": 18202,
"self": 0.31643783899227174,
"children": {
"env_step": {
"total": 473.590625495009,
"count": 18202,
"self": 327.78519822701855,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.4880513459998,
"count": 18202,
"self": 1.5931924990081257,
"children": {
"TorchPolicy.evaluate": {
"total": 143.89485884699167,
"count": 18202,
"self": 33.125923810995744,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.76893503599592,
"count": 18202,
"self": 110.76893503599592
}
}
}
}
},
"workers": {
"total": 0.3173759219906742,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.48024317600294,
"count": 18202,
"is_parallel": true,
"self": 231.69878175600167,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006062331000009635,
"count": 1,
"is_parallel": true,
"self": 0.00397462699999096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020877040000186753,
"count": 10,
"is_parallel": true,
"self": 0.0020877040000186753
}
}
},
"UnityEnvironment.step": {
"total": 0.041979733000005126,
"count": 1,
"is_parallel": true,
"self": 0.0005431450001083249,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029429599999275524,
"count": 1,
"is_parallel": true,
"self": 0.00029429599999275524
},
"communicator.exchange": {
"total": 0.03934556099994779,
"count": 1,
"is_parallel": true,
"self": 0.03934556099994779
},
"steps_from_proto": {
"total": 0.001796730999956253,
"count": 1,
"is_parallel": true,
"self": 0.0003941900000654641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001402540999890789,
"count": 10,
"is_parallel": true,
"self": 0.001402540999890789
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 250.78146142000128,
"count": 18201,
"is_parallel": true,
"self": 10.170614036987615,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5644260809961565,
"count": 18201,
"is_parallel": true,
"self": 5.5644260809961565
},
"communicator.exchange": {
"total": 202.76730794501026,
"count": 18201,
"is_parallel": true,
"self": 202.76730794501026
},
"steps_from_proto": {
"total": 32.27911335700725,
"count": 18201,
"is_parallel": true,
"self": 7.366313782998759,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.91279957400849,
"count": 182010,
"is_parallel": true,
"self": 24.91279957400849
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001203859999350243,
"count": 1,
"self": 0.0001203859999350243,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.47018176198804,
"count": 427744,
"is_parallel": true,
"self": 10.660357168029805,
"children": {
"process_trajectory": {
"total": 269.2292788829589,
"count": 427744,
"is_parallel": true,
"self": 268.460466903959,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7688119789999064,
"count": 4,
"is_parallel": true,
"self": 0.7688119789999064
}
}
},
"_update_policy": {
"total": 190.58054571099933,
"count": 90,
"is_parallel": true,
"self": 67.01531909400171,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.56522661699762,
"count": 4584,
"is_parallel": true,
"self": 123.56522661699762
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12151960699998199,
"count": 1,
"self": 0.0009306370000103925,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1205889699999716,
"count": 1,
"self": 0.1205889699999716
}
}
}
}
}
}
}