ppo-Pyramids / run_logs /timers.json
Enzogbs's picture
First Push
8f95f7b verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.7861396074295044,
"min": 0.7861396074295044,
"max": 0.872287929058075,
"count": 4
},
"Pyramids.Policy.Entropy.sum": {
"value": 23584.1875,
"min": 9378.83984375,
"max": 25795.201171875,
"count": 4
},
"Pyramids.Step.mean": {
"value": 599915.0,
"min": 509962.0,
"max": 599915.0,
"count": 4
},
"Pyramids.Step.sum": {
"value": 599915.0,
"min": 509962.0,
"max": 599915.0,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.21687014400959015,
"min": 0.18975910544395447,
"max": 0.25367432832717896,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 55.30188751220703,
"min": 16.12952423095703,
"max": 64.43328094482422,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.07572141289710999,
"min": -0.0005947133176960051,
"max": 0.08187860995531082,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 19.3089599609375,
"min": -0.14927303791046143,
"max": 20.79716682434082,
"count": 4
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 598.58,
"min": 367.6363636363636,
"max": 688.0,
"count": 4
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29929.0,
"min": 4044.0,
"max": 31093.0,
"count": 4
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9612879778444767,
"min": 0.733977733221319,
"max": 1.6323636269027537,
"count": 4
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 48.064398892223835,
"min": 17.95599989593029,
"max": 48.90059792250395,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9612879778444767,
"min": 0.733977733221319,
"max": 1.6323636269027537,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 48.064398892223835,
"min": 17.95599989593029,
"max": 48.90059792250395,
"count": 4
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08766225127736106,
"min": 0.06557353724598546,
"max": 0.10796268726699054,
"count": 4
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.383112563868053,
"min": 0.72130890970584,
"max": 4.858320927014574,
"count": 4
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07300172424930637,
"min": 0.06846027944277647,
"max": 0.07300172424930637,
"count": 4
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0220241394902891,
"min": 0.28459965959579375,
"max": 1.0552715627732232,
"count": 4
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011815740849280179,
"min": 0.008918849865949596,
"max": 0.012577493454767559,
"count": 4
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1654203718899225,
"min": 0.035675399463798385,
"max": 0.1886624018215134,
"count": 4
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.160419041797617e-06,
"min": 7.160419041797617e-06,
"max": 4.7411209196291655e-05,
"count": 4
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010024586658516664,
"min": 0.00010024586658516664,
"max": 0.0005297297234238333,
"count": 4
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10238677380952381,
"min": 0.10238677380952381,
"max": 0.11580370833333335,
"count": 4
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4334148333333334,
"min": 0.4632148333333334,
"max": 1.6123261666666668,
"count": 4
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002484387035714285,
"min": 0.0002484387035714285,
"max": 0.0015887904624999995,
"count": 4
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0034781418499999993,
"min": 0.0034781418499999993,
"max": 0.017779959050000002,
"count": 4
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01409356389194727,
"min": 0.01409356389194727,
"max": 0.015538031235337257,
"count": 4
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19730989634990692,
"min": 0.06215212494134903,
"max": 0.21933189034461975,
"count": 4
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750786708",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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 --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750786949"
},
"total": 240.85364855599983,
"count": 1,
"self": 0.772170990000177,
"children": {
"run_training.setup": {
"total": 0.02129591699986122,
"count": 1,
"self": 0.02129591699986122
},
"TrainerController.start_learning": {
"total": 240.0601816489998,
"count": 1,
"self": 0.1739789830130576,
"children": {
"TrainerController._reset_env": {
"total": 2.230708729000071,
"count": 1,
"self": 2.230708729000071
},
"TrainerController.advance": {
"total": 237.5376551319864,
"count": 6447,
"self": 0.18162194294700384,
"children": {
"env_step": {
"total": 170.6860607320309,
"count": 6447,
"self": 153.00856305203297,
"children": {
"SubprocessEnvManager._take_step": {
"total": 17.57545113601327,
"count": 6447,
"self": 0.5195601990358227,
"children": {
"TorchPolicy.evaluate": {
"total": 17.05589093697745,
"count": 6319,
"self": 17.05589093697745
}
}
},
"workers": {
"total": 0.10204654398467028,
"count": 6447,
"self": 0.0,
"children": {
"worker_root": {
"total": 239.26220040202452,
"count": 6447,
"is_parallel": true,
"self": 99.72550172299725,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001841798999976163,
"count": 1,
"is_parallel": true,
"self": 0.0006007889996908489,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012410100002853142,
"count": 8,
"is_parallel": true,
"self": 0.0012410100002853142
}
}
},
"UnityEnvironment.step": {
"total": 0.05242421499997363,
"count": 1,
"is_parallel": true,
"self": 0.0005473109999911685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047382699995068833,
"count": 1,
"is_parallel": true,
"self": 0.00047382699995068833
},
"communicator.exchange": {
"total": 0.049717719000000216,
"count": 1,
"is_parallel": true,
"self": 0.049717719000000216
},
"steps_from_proto": {
"total": 0.001685358000031556,
"count": 1,
"is_parallel": true,
"self": 0.00036290900061430875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013224489994172473,
"count": 8,
"is_parallel": true,
"self": 0.0013224489994172473
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 139.53669867902727,
"count": 6446,
"is_parallel": true,
"self": 3.459537209050268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.5212421239843934,
"count": 6446,
"is_parallel": true,
"self": 2.5212421239843934
},
"communicator.exchange": {
"total": 123.02307108398963,
"count": 6446,
"is_parallel": true,
"self": 123.02307108398963
},
"steps_from_proto": {
"total": 10.532848262002972,
"count": 6446,
"is_parallel": true,
"self": 2.2658241069807445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 8.267024155022227,
"count": 51568,
"is_parallel": true,
"self": 8.267024155022227
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 66.6699724570085,
"count": 6447,
"self": 0.33857554703172354,
"children": {
"process_trajectory": {
"total": 13.62294030197745,
"count": 6447,
"self": 13.500918556977467,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12202174499998364,
"count": 1,
"self": 0.12202174499998364
}
}
},
"_update_policy": {
"total": 52.708456607999324,
"count": 47,
"self": 29.19401524999421,
"children": {
"TorchPPOOptimizer.update": {
"total": 23.514441358005115,
"count": 2265,
"self": 23.514441358005115
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1380002433725167e-06,
"count": 1,
"self": 1.1380002433725167e-06
},
"TrainerController._save_models": {
"total": 0.11783766700000342,
"count": 1,
"self": 0.001704941999832954,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11613272500017047,
"count": 1,
"self": 0.11613272500017047
}
}
}
}
}
}
}