arnonl's picture
push1
b0718fb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.994524359703064,
"min": 0.994524359703064,
"max": 2.871279001235962,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9495.71875,
"min": 9495.71875,
"max": 29404.767578125,
"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": 12.994120597839355,
"min": 0.28829681873321533,
"max": 12.994120597839355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2533.853515625,
"min": 55.92958068847656,
"max": 2658.97314453125,
"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": 0.06451068685604625,
"min": 0.061039212250662056,
"max": 0.07605163341841213,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.258042747424185,
"min": 0.25044888519001757,
"max": 0.37048686811713016,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2052733365665464,
"min": 0.11713555730267555,
"max": 0.2938641131508584,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8210933462661856,
"min": 0.4685422292107022,
"max": 1.469320565754292,
"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": 25.772727272727273,
"min": 3.2045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 141.0,
"max": 1409.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.2045454545454546,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 141.0,
"max": 1409.0,
"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": "1674119857",
"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": "1.21.6",
"end_time_seconds": "1674120282"
},
"total": 425.200528512,
"count": 1,
"self": 0.3739375850001352,
"children": {
"run_training.setup": {
"total": 0.11246199899994735,
"count": 1,
"self": 0.11246199899994735
},
"TrainerController.start_learning": {
"total": 424.7141289279999,
"count": 1,
"self": 0.48324580900225556,
"children": {
"TrainerController._reset_env": {
"total": 9.370825417999981,
"count": 1,
"self": 9.370825417999981
},
"TrainerController.advance": {
"total": 414.74600765899754,
"count": 18202,
"self": 0.2534848889947625,
"children": {
"env_step": {
"total": 414.4925227700028,
"count": 18202,
"self": 271.19708432100856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.0419653349993,
"count": 18202,
"self": 1.3641749890042547,
"children": {
"TorchPolicy.evaluate": {
"total": 141.67779034599505,
"count": 18202,
"self": 31.47176383499766,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.20602651099739,
"count": 18202,
"self": 110.20602651099739
}
}
}
}
},
"workers": {
"total": 0.25347311399491446,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.565961210001,
"count": 18202,
"is_parallel": true,
"self": 204.9662696180036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005368242000031387,
"count": 1,
"is_parallel": true,
"self": 0.003167282999811505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002200959000219882,
"count": 10,
"is_parallel": true,
"self": 0.002200959000219882
}
}
},
"UnityEnvironment.step": {
"total": 0.0415206530000205,
"count": 1,
"is_parallel": true,
"self": 0.00044808600000578735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029963400004362484,
"count": 1,
"is_parallel": true,
"self": 0.00029963400004362484
},
"communicator.exchange": {
"total": 0.03889432300002227,
"count": 1,
"is_parallel": true,
"self": 0.03889432300002227
},
"steps_from_proto": {
"total": 0.0018786099999488215,
"count": 1,
"is_parallel": true,
"self": 0.0004460210001298037,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014325889998190178,
"count": 10,
"is_parallel": true,
"self": 0.0014325889998190178
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.59969159199738,
"count": 18201,
"is_parallel": true,
"self": 8.15961913298986,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.834608764001814,
"count": 18201,
"is_parallel": true,
"self": 4.834608764001814
},
"communicator.exchange": {
"total": 173.17093732499654,
"count": 18201,
"is_parallel": true,
"self": 173.17093732499654
},
"steps_from_proto": {
"total": 32.434526370009166,
"count": 18201,
"is_parallel": true,
"self": 6.351950986014117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.08257538399505,
"count": 182010,
"is_parallel": true,
"self": 26.08257538399505
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.039700002067548e-05,
"count": 1,
"self": 4.039700002067548e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 411.86389821500404,
"count": 335720,
"is_parallel": true,
"self": 9.08201754499919,
"children": {
"process_trajectory": {
"total": 235.47424289800506,
"count": 335720,
"is_parallel": true,
"self": 234.71195733700506,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7622855609999988,
"count": 4,
"is_parallel": true,
"self": 0.7622855609999988
}
}
},
"_update_policy": {
"total": 167.3076377719998,
"count": 90,
"is_parallel": true,
"self": 43.42694808200201,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.88068968999778,
"count": 4587,
"is_parallel": true,
"self": 123.88068968999778
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11400964500012378,
"count": 1,
"self": 0.000899680000202352,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11310996499992143,
"count": 1,
"self": 0.11310996499992143
}
}
}
}
}
}
}