tslai1992's picture
First Push
c6aac06
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9446055293083191,
"min": 0.930646538734436,
"max": 2.8733572959899902,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9019.09375,
"min": 9019.09375,
"max": 29489.265625,
"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": 11.86700439453125,
"min": 0.3033011555671692,
"max": 11.86700439453125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2314.06591796875,
"min": 58.840423583984375,
"max": 2409.57666015625,
"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": 0.06960264489082998,
"min": 0.06553082848190303,
"max": 0.07999544514956035,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27841057956331994,
"min": 0.2621233139276121,
"max": 0.3707249384543484,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1903088329104232,
"min": 0.1197387677829658,
"max": 0.28354026499916524,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7612353316416928,
"min": 0.4789550711318632,
"max": 1.4177013249958261,
"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": 23.886363636363637,
"min": 3.090909090909091,
"max": 23.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1051.0,
"min": 136.0,
"max": 1288.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.886363636363637,
"min": 3.090909090909091,
"max": 23.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1051.0,
"min": 136.0,
"max": 1288.0,
"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": "1690108183",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690108668"
},
"total": 484.8763215040001,
"count": 1,
"self": 0.43224890300018615,
"children": {
"run_training.setup": {
"total": 0.041098242999964896,
"count": 1,
"self": 0.041098242999964896
},
"TrainerController.start_learning": {
"total": 484.40297435799994,
"count": 1,
"self": 0.5790212590060264,
"children": {
"TrainerController._reset_env": {
"total": 5.2401752670000405,
"count": 1,
"self": 5.2401752670000405
},
"TrainerController.advance": {
"total": 478.44670994099386,
"count": 18202,
"self": 0.28283924599224974,
"children": {
"env_step": {
"total": 478.1638706950016,
"count": 18202,
"self": 346.6327043439866,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.23695123401274,
"count": 18202,
"self": 2.019905166008243,
"children": {
"TorchPolicy.evaluate": {
"total": 129.2170460680045,
"count": 18202,
"self": 129.2170460680045
}
}
},
"workers": {
"total": 0.2942151170022953,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 482.77473083000575,
"count": 18202,
"is_parallel": true,
"self": 228.13302580301092,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0050109840000232,
"count": 1,
"is_parallel": true,
"self": 0.0035677590004752346,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014432249995479651,
"count": 10,
"is_parallel": true,
"self": 0.0014432249995479651
}
}
},
"UnityEnvironment.step": {
"total": 0.04258328299999903,
"count": 1,
"is_parallel": true,
"self": 0.0005405949999612858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003809920000321654,
"count": 1,
"is_parallel": true,
"self": 0.0003809920000321654
},
"communicator.exchange": {
"total": 0.03949200400006703,
"count": 1,
"is_parallel": true,
"self": 0.03949200400006703
},
"steps_from_proto": {
"total": 0.00216969199993855,
"count": 1,
"is_parallel": true,
"self": 0.0005129429999897184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016567489999488316,
"count": 10,
"is_parallel": true,
"self": 0.0016567489999488316
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.64170502699483,
"count": 18201,
"is_parallel": true,
"self": 10.94208585099625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.4244607659970825,
"count": 18201,
"is_parallel": true,
"self": 5.4244607659970825
},
"communicator.exchange": {
"total": 202.34842471400293,
"count": 18201,
"is_parallel": true,
"self": 202.34842471400293
},
"steps_from_proto": {
"total": 35.926733695998564,
"count": 18201,
"is_parallel": true,
"self": 6.674583413995151,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.252150282003413,
"count": 182010,
"is_parallel": true,
"self": 29.252150282003413
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011244699999224395,
"count": 1,
"self": 0.00011244699999224395,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 474.5439587259759,
"count": 441142,
"is_parallel": true,
"self": 10.478763159923687,
"children": {
"process_trajectory": {
"total": 259.41967179205164,
"count": 441142,
"is_parallel": true,
"self": 258.13076243905164,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2889093530000082,
"count": 4,
"is_parallel": true,
"self": 1.2889093530000082
}
}
},
"_update_policy": {
"total": 204.6455237740006,
"count": 90,
"is_parallel": true,
"self": 78.26687068999524,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.37865308400535,
"count": 4584,
"is_parallel": true,
"self": 126.37865308400535
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1369554440000229,
"count": 1,
"self": 0.0009152159998393472,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13604022800018356,
"count": 1,
"self": 0.13604022800018356
}
}
}
}
}
}
}