testpyramidsrnd / run_logs /timers.json
fumi13's picture
First Pyramids
61be823
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5098435282707214,
"min": 0.5087623000144958,
"max": 1.4478379487991333,
"count": 16
},
"Pyramids.Policy.Entropy.sum": {
"value": 15417.66796875,
"min": 15083.78515625,
"max": 43921.61328125,
"count": 16
},
"Pyramids.Step.mean": {
"value": 479994.0,
"min": 29952.0,
"max": 479994.0,
"count": 16
},
"Pyramids.Step.sum": {
"value": 479994.0,
"min": 29952.0,
"max": 479994.0,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.057745445519685745,
"min": -0.2257632166147232,
"max": 0.012231298722326756,
"count": 16
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -14.032143592834473,
"min": -53.505882263183594,
"max": 2.972205638885498,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02860564924776554,
"min": 0.02841412089765072,
"max": 0.5475939512252808,
"count": 16
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.951172828674316,
"min": 6.847803115844727,
"max": 129.77976989746094,
"count": 16
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0688666013303912,
"min": 0.06557281728961548,
"max": 0.07654574527127067,
"count": 16
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9641324186254767,
"min": 0.4960725721755953,
"max": 0.9991619324639175,
"count": 16
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002181511497640351,
"min": 0.0009248920477950042,
"max": 0.010818158059889501,
"count": 16
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.030541160966964912,
"min": 0.007913541676264256,
"max": 0.0757271064192265,
"count": 16
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.0937435878028566e-05,
"min": 2.0937435878028566e-05,
"max": 0.00029030126037577137,
"count": 16
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00029312410229239994,
"min": 0.00029312410229239994,
"max": 0.0026251899249368,
"count": 16
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1069791142857143,
"min": 0.1069791142857143,
"max": 0.19676708571428575,
"count": 16
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4977076000000002,
"min": 1.3382272,
"max": 2.1686938,
"count": 16
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0007072135171428571,
"min": 0.0007072135171428571,
"max": 0.00967703186285714,
"count": 16
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00990098924,
"min": 0.00990098924,
"max": 0.08753881368000001,
"count": 16
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.022975115105509758,
"min": 0.022975115105509758,
"max": 0.5410431027412415,
"count": 16
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3216516077518463,
"min": 0.3216516077518463,
"max": 3.787301540374756,
"count": 16
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 924.7575757575758,
"min": 905.7428571428571,
"max": 999.0,
"count": 16
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30517.0,
"min": 15984.0,
"max": 32687.0,
"count": 16
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.7567437975667417,
"min": -1.0000000521540642,
"max": -0.3726000501350923,
"count": 16
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -24.215801522135735,
"min": -32.000001668930054,
"max": -12.295801654458046,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.7567437975667417,
"min": -1.0000000521540642,
"max": -0.3726000501350923,
"count": 16
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -24.215801522135735,
"min": -32.000001668930054,
"max": -12.295801654458046,
"count": 16
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.22409057037293678,
"min": 0.22409057037293678,
"max": 11.42012949846685,
"count": 16
},
"Pyramids.Policy.RndReward.sum": {
"value": 7.170898251933977,
"min": 7.170898251933977,
"max": 182.7220719754696,
"count": 16
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 16
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1667127624",
"python_version": "3.7.15 (default, Oct 12 2022, 19:14:55) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1667128493"
},
"total": 869.1740032770001,
"count": 1,
"self": 0.27499457099997926,
"children": {
"run_training.setup": {
"total": 0.044834185000127036,
"count": 1,
"self": 0.044834185000127036
},
"TrainerController.start_learning": {
"total": 868.854174521,
"count": 1,
"self": 0.7197349079899595,
"children": {
"TrainerController._reset_env": {
"total": 6.5234585589998915,
"count": 1,
"self": 6.5234585589998915
},
"TrainerController.advance": {
"total": 861.5187838220099,
"count": 31557,
"self": 0.7656324240413142,
"children": {
"env_step": {
"total": 505.8749584779789,
"count": 31557,
"self": 450.37221667104154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.10876086897042,
"count": 31557,
"self": 2.3881238949766157,
"children": {
"TorchPolicy.evaluate": {
"total": 52.720636973993805,
"count": 31315,
"self": 17.45509013198034,
"children": {
"TorchPolicy.sample_actions": {
"total": 35.265546842013464,
"count": 31315,
"self": 35.265546842013464
}
}
}
}
},
"workers": {
"total": 0.3939809379669441,
"count": 31557,
"self": 0.0,
"children": {
"worker_root": {
"total": 867.5323795799857,
"count": 31557,
"is_parallel": true,
"self": 467.122846197989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004504079999833266,
"count": 1,
"is_parallel": true,
"self": 0.0032424319995243422,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012616480003089237,
"count": 8,
"is_parallel": true,
"self": 0.0012616480003089237
}
}
},
"UnityEnvironment.step": {
"total": 0.035815299999967465,
"count": 1,
"is_parallel": true,
"self": 0.0003513099998144753,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002923140000348212,
"count": 1,
"is_parallel": true,
"self": 0.0002923140000348212
},
"communicator.exchange": {
"total": 0.03403479700000389,
"count": 1,
"is_parallel": true,
"self": 0.03403479700000389
},
"steps_from_proto": {
"total": 0.001136879000114277,
"count": 1,
"is_parallel": true,
"self": 0.00031141600038608885,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008254629997281882,
"count": 8,
"is_parallel": true,
"self": 0.0008254629997281882
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 400.40953338199665,
"count": 31556,
"is_parallel": true,
"self": 9.197202508956707,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.097467067007528,
"count": 31556,
"is_parallel": true,
"self": 7.097467067007528
},
"communicator.exchange": {
"total": 345.34410980503117,
"count": 31556,
"is_parallel": true,
"self": 345.34410980503117
},
"steps_from_proto": {
"total": 38.77075400100125,
"count": 31556,
"is_parallel": true,
"self": 9.139076035082326,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.631677965918925,
"count": 252448,
"is_parallel": true,
"self": 29.631677965918925
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 354.8781929199897,
"count": 31557,
"self": 1.1741882180240282,
"children": {
"process_trajectory": {
"total": 82.23322858596907,
"count": 31557,
"self": 82.12624872296897,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10697986300010598,
"count": 1,
"self": 0.10697986300010598
}
}
},
"_update_policy": {
"total": 271.4707761159966,
"count": 205,
"self": 108.37250721897453,
"children": {
"TorchPPOOptimizer.update": {
"total": 163.09826889702208,
"count": 11430,
"self": 163.09826889702208
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2420000530255493e-06,
"count": 1,
"self": 1.2420000530255493e-06
},
"TrainerController._save_models": {
"total": 0.09219599000016387,
"count": 1,
"self": 0.0016091460001916857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09058684399997219,
"count": 1,
"self": 0.09058684399997219
}
}
}
}
}
}
}