ppo-PyramidsRND / run_logs /timers.json
vvn0's picture
First Push
5e6b207
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.16412334144115448,
"min": 0.15604618191719055,
"max": 1.384837031364441,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4910.5703125,
"min": 4713.84326171875,
"max": 42010.41796875,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999915.0,
"min": 29952.0,
"max": 2999915.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999915.0,
"min": 29952.0,
"max": 2999915.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.8371778726577759,
"min": -0.10320615023374557,
"max": 0.9067159295082092,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 257.01361083984375,
"min": -24.872682571411133,
"max": 286.229736328125,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015303094871342182,
"min": -0.007398901041597128,
"max": 0.5556513071060181,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.698050022125244,
"min": -2.127768039703369,
"max": 131.68936157226562,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06732675624331094,
"min": 0.06501314707011692,
"max": 0.07368486087722269,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0099013436496642,
"min": 0.48797129034318953,
"max": 1.0915998800289042,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015224370395755579,
"min": 0.00018740376750943672,
"max": 0.018807780661382802,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22836555593633368,
"min": 0.002623652745132114,
"max": 0.28211670992074206,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5246794918066666e-06,
"min": 1.5246794918066666e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2870192377099998e-05,
"min": 2.2870192377099998e-05,
"max": 0.0039690564769812,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050819333333334,
"min": 0.10050819333333334,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5076229,
"min": 1.3962282666666668,
"max": 2.7674816666666673,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.076851400000001e-05,
"min": 6.076851400000001e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0009115277100000002,
"min": 0.0009115277100000002,
"max": 0.13230957812000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007662598509341478,
"min": 0.00684213126078248,
"max": 0.4987165629863739,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11493897438049316,
"min": 0.095789834856987,
"max": 3.491015911102295,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 215.28671328671328,
"min": 193.43790849673204,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30786.0,
"min": 15984.0,
"max": 32775.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7427440385718447,
"min": -1.0000000521540642,
"max": 1.806474012213868,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 249.21239751577377,
"min": -31.995201662182808,
"max": 278.19699788093567,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7427440385718447,
"min": -1.0000000521540642,
"max": 1.806474012213868,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 249.21239751577377,
"min": -31.995201662182808,
"max": 278.19699788093567,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01683859440349075,
"min": 0.015086183522560697,
"max": 10.160925563424826,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.407918999699177,
"min": 2.075366360557382,
"max": 162.5748090147972,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675851806",
"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/PyramidsRND.yaml --env=./training-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": "1675859237"
},
"total": 7431.0571472130005,
"count": 1,
"self": 0.4904983309997988,
"children": {
"run_training.setup": {
"total": 0.19040901700003587,
"count": 1,
"self": 0.19040901700003587
},
"TrainerController.start_learning": {
"total": 7430.376239865001,
"count": 1,
"self": 3.8415989761324454,
"children": {
"TrainerController._reset_env": {
"total": 9.096649476000039,
"count": 1,
"self": 9.096649476000039
},
"TrainerController.advance": {
"total": 7417.344206518868,
"count": 195387,
"self": 4.221855558738753,
"children": {
"env_step": {
"total": 5202.904304674099,
"count": 195387,
"self": 4868.984584972139,
"children": {
"SubprocessEnvManager._take_step": {
"total": 331.3992727280297,
"count": 195387,
"self": 13.852460311223979,
"children": {
"TorchPolicy.evaluate": {
"total": 317.5468124168057,
"count": 187564,
"self": 107.43239118379654,
"children": {
"TorchPolicy.sample_actions": {
"total": 210.11442123300918,
"count": 187564,
"self": 210.11442123300918
}
}
}
}
},
"workers": {
"total": 2.5204469739304614,
"count": 195387,
"self": 0.0,
"children": {
"worker_root": {
"total": 7415.007759046017,
"count": 195387,
"is_parallel": true,
"self": 2888.899119553027,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004671111000050132,
"count": 1,
"is_parallel": true,
"self": 0.0025128950001089834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021582159999411488,
"count": 8,
"is_parallel": true,
"self": 0.0021582159999411488
}
}
},
"UnityEnvironment.step": {
"total": 0.04646013699999685,
"count": 1,
"is_parallel": true,
"self": 0.0005470670000136124,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004545799999959854,
"count": 1,
"is_parallel": true,
"self": 0.0004545799999959854
},
"communicator.exchange": {
"total": 0.04370295100000021,
"count": 1,
"is_parallel": true,
"self": 0.04370295100000021
},
"steps_from_proto": {
"total": 0.0017555389999870386,
"count": 1,
"is_parallel": true,
"self": 0.0005457649999698333,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012097740000172053,
"count": 8,
"is_parallel": true,
"self": 0.0012097740000172053
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4526.10863949299,
"count": 195386,
"is_parallel": true,
"self": 94.28391108807409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 68.59874834694165,
"count": 195386,
"is_parallel": true,
"self": 68.59874834694165
},
"communicator.exchange": {
"total": 4081.6811111521592,
"count": 195386,
"is_parallel": true,
"self": 4081.6811111521592
},
"steps_from_proto": {
"total": 281.5448689058151,
"count": 195386,
"is_parallel": true,
"self": 66.59710814326803,
"children": {
"_process_rank_one_or_two_observation": {
"total": 214.9477607625471,
"count": 1563088,
"is_parallel": true,
"self": 214.9477607625471
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2210.2180462860306,
"count": 195387,
"self": 8.01516532609412,
"children": {
"process_trajectory": {
"total": 491.02128832095093,
"count": 195387,
"self": 490.27149987594987,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7497884450010588,
"count": 6,
"self": 0.7497884450010588
}
}
},
"_update_policy": {
"total": 1711.1815926389856,
"count": 1394,
"self": 658.6758141998787,
"children": {
"TorchPPOOptimizer.update": {
"total": 1052.505778439107,
"count": 68400,
"self": 1052.505778439107
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.480001270072535e-07,
"count": 1,
"self": 8.480001270072535e-07
},
"TrainerController._save_models": {
"total": 0.09378404600010981,
"count": 1,
"self": 0.0014700329993502237,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09231401300075959,
"count": 1,
"self": 0.09231401300075959
}
}
}
}
}
}
}