archbold's picture
Second Push
ee5ec22 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.3090474605560303,
"min": 1.3090474605560303,
"max": 1.6092250347137451,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 2680.92919921875,
"min": 2680.92919921875,
"max": 6591.3857421875,
"count": 10
},
"Pyramids.Step.mean": {
"value": 29952.0,
"min": 2944.0,
"max": 29952.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 29952.0,
"min": 2944.0,
"max": 29952.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.03365251421928406,
"min": -0.03365251421928406,
"max": 0.06276223808526993,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.8076603412628174,
"min": -0.8076603412628174,
"max": 1.5062936544418335,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.5827732086181641,
"min": -0.014214863069355488,
"max": 0.6903865337371826,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 13.986557006835938,
"min": -0.3269418478012085,
"max": 17.259662628173828,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06393464656624322,
"min": 0.06087110819256244,
"max": 0.07764413797607024,
"count": 7
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.06393464656624322,
"min": 0.06087110819256244,
"max": 0.07764413797607024,
"count": 7
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0013999569837324088,
"min": 0.0013999569837324088,
"max": 0.03380898640413458,
"count": 7
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0013999569837324088,
"min": 0.0013999569837324088,
"max": 0.03380898640413458,
"count": 7
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.7120094293333343e-05,
"min": 1.7120094293333343e-05,
"max": 0.0002590400136533332,
"count": 7
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.7120094293333343e-05,
"min": 1.7120094293333343e-05,
"max": 0.0002590400136533332,
"count": 7
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10570666666666663,
"min": 0.10570666666666663,
"max": 0.18634666666666666,
"count": 7
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.10570666666666663,
"min": 0.10570666666666663,
"max": 0.18634666666666666,
"count": 7
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005800960000000005,
"min": 0.0005800960000000005,
"max": 0.008636032,
"count": 7
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0005800960000000005,
"min": 0.0005800960000000005,
"max": 0.008636032,
"count": 7
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.2728302776813507,
"min": 0.26073023676872253,
"max": 1.656243920326233,
"count": 7
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2728302776813507,
"min": 0.26073023676872253,
"max": 1.656243920326233,
"count": 7
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 15984.0,
"min": 15984.0,
"max": 15984.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 2
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -10.000000521540642,
"min": -10.000000521540642,
"max": -6.000000312924385,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 2
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -10.000000521540642,
"min": -10.000000521540642,
"max": -6.000000312924385,
"count": 2
},
"Pyramids.Policy.RndReward.mean": {
"value": 13.632160347700118,
"min": 13.632160347700118,
"max": 14.692820837100347,
"count": 2
},
"Pyramids.Policy.RndReward.sum": {
"value": 136.3216034770012,
"min": 88.15692502260208,
"max": 136.3216034770012,
"count": 2
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714795083",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714795144"
},
"total": 61.15798925900003,
"count": 1,
"self": 0.4929876140001852,
"children": {
"run_training.setup": {
"total": 0.049556191999954535,
"count": 1,
"self": 0.049556191999954535
},
"TrainerController.start_learning": {
"total": 60.61544545299989,
"count": 1,
"self": 0.047954513002650856,
"children": {
"TrainerController._reset_env": {
"total": 2.2288440849999915,
"count": 1,
"self": 2.2288440849999915
},
"TrainerController.advance": {
"total": 58.215163778997294,
"count": 1896,
"self": 0.048030980008206825,
"children": {
"env_step": {
"total": 38.512420580992966,
"count": 1896,
"self": 34.01890935899587,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4.465514426000027,
"count": 1896,
"self": 0.1469552779958576,
"children": {
"TorchPolicy.evaluate": {
"total": 4.318559148004169,
"count": 1896,
"self": 4.318559148004169
}
}
},
"workers": {
"total": 0.027996795997069057,
"count": 1896,
"self": 0.0,
"children": {
"worker_root": {
"total": 60.19534272899705,
"count": 1896,
"is_parallel": true,
"self": 29.91926973799059,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020238710001194704,
"count": 1,
"is_parallel": true,
"self": 0.0005980250002721732,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014258459998472972,
"count": 8,
"is_parallel": true,
"self": 0.0014258459998472972
}
}
},
"UnityEnvironment.step": {
"total": 0.049396006000051784,
"count": 1,
"is_parallel": true,
"self": 0.0006365579999965121,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000432063000062044,
"count": 1,
"is_parallel": true,
"self": 0.000432063000062044
},
"communicator.exchange": {
"total": 0.04661451800006944,
"count": 1,
"is_parallel": true,
"self": 0.04661451800006944
},
"steps_from_proto": {
"total": 0.00171286699992379,
"count": 1,
"is_parallel": true,
"self": 0.0003614569995988859,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001351410000324904,
"count": 8,
"is_parallel": true,
"self": 0.001351410000324904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 30.27607299100646,
"count": 1895,
"is_parallel": true,
"self": 1.0839517280167001,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.7137827979963731,
"count": 1895,
"is_parallel": true,
"self": 0.7137827979963731
},
"communicator.exchange": {
"total": 25.434320517997094,
"count": 1895,
"is_parallel": true,
"self": 25.434320517997094
},
"steps_from_proto": {
"total": 3.0440179469962914,
"count": 1895,
"is_parallel": true,
"self": 0.6353762249984811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 2.4086417219978102,
"count": 15160,
"is_parallel": true,
"self": 2.4086417219978102
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 19.65471221799612,
"count": 1896,
"self": 0.06004638199465262,
"children": {
"process_trajectory": {
"total": 3.997304165001424,
"count": 1896,
"self": 3.997304165001424
},
"_update_policy": {
"total": 15.597361671000044,
"count": 7,
"self": 8.883594716996868,
"children": {
"TorchPPOOptimizer.update": {
"total": 6.713766954003177,
"count": 663,
"self": 6.713766954003177
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.290001798945013e-07,
"count": 1,
"self": 9.290001798945013e-07
},
"TrainerController._save_models": {
"total": 0.12348214699977689,
"count": 1,
"self": 0.0017281409996030561,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12175400600017383,
"count": 1,
"self": 0.12175400600017383
}
}
}
}
}
}
}