|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.21478991210460663, |
|
"min": 0.20587411522865295, |
|
"max": 0.6635094881057739, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 6319.978515625, |
|
"min": 6199.28125, |
|
"max": 19681.1171875, |
|
"count": 67 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 202.09923664122138, |
|
"min": 170.33333333333334, |
|
"max": 324.7980769230769, |
|
"count": 67 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 26475.0, |
|
"min": 7154.0, |
|
"max": 34209.0, |
|
"count": 67 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999953.0, |
|
"min": 1019985.0, |
|
"max": 2999953.0, |
|
"count": 67 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999953.0, |
|
"min": 1019985.0, |
|
"max": 2999953.0, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.8460010290145874, |
|
"min": 0.3994930684566498, |
|
"max": 0.8886299133300781, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 256.33831787109375, |
|
"min": 69.91128540039062, |
|
"max": 272.80938720703125, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.007474419195204973, |
|
"min": -0.0037378580309450626, |
|
"max": 0.14753714203834534, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.264749050140381, |
|
"min": -1.1325709819793701, |
|
"max": 41.162864685058594, |
|
"count": 67 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.781787680891844, |
|
"min": 1.5963942678911345, |
|
"max": 1.8296666578167962, |
|
"count": 67 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 231.6323985159397, |
|
"min": 76.84599962830544, |
|
"max": 271.7899979650974, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.781787680891844, |
|
"min": 1.5963942678911345, |
|
"max": 1.8296666578167962, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 231.6323985159397, |
|
"min": 76.84599962830544, |
|
"max": 271.7899979650974, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.01764767567085353, |
|
"min": 0.01764767567085353, |
|
"max": 0.0433384377005831, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.294197837210959, |
|
"min": 1.0528611817280762, |
|
"max": 4.4638590831600595, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07035031930100792, |
|
"min": 0.06295160259208538, |
|
"max": 0.07553702230152416, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.984904470214111, |
|
"min": 0.49356065462367016, |
|
"max": 1.0765698625045306, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015417234234564137, |
|
"min": 0.010701739972919974, |
|
"max": 0.01728356775570527, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.21584127928389793, |
|
"min": 0.07491217981043982, |
|
"max": 0.259253516335579, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5107137821761932e-06, |
|
"min": 1.5107137821761932e-06, |
|
"max": 0.00019898423367193334, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.1149992950466706e-05, |
|
"min": 2.1149992950466706e-05, |
|
"max": 0.0027086627971125666, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050353809523813, |
|
"min": 0.10050353809523813, |
|
"max": 0.1663280666666667, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4070495333333337, |
|
"min": 1.1642964666666669, |
|
"max": 2.3028874333333333, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.0303455714285815e-05, |
|
"min": 6.0303455714285815e-05, |
|
"max": 0.00663617386, |
|
"count": 67 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008442483800000014, |
|
"min": 0.0008442483800000014, |
|
"max": 0.09033845459, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.008308643475174904, |
|
"min": 0.008308643475174904, |
|
"max": 0.01302468590438366, |
|
"count": 67 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.11632100492715836, |
|
"min": 0.09067335724830627, |
|
"max": 0.18112194538116455, |
|
"count": 67 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 67 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 67 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1682280256", |
|
"python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", |
|
"command_line_arguments": "/home/byron/miniconda3/envs/torch/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./ml-agents/training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids-Training2 --no-graphics --torch-device=cuda:0 --num-envs 8 --num-areas 8 --resume --env-args -batchmode", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.13.1+cu117", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1682282200" |
|
}, |
|
"total": 1943.9294684159977, |
|
"count": 1, |
|
"self": 0.6761621149926214, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.028145499003585428, |
|
"count": 1, |
|
"self": 0.028145499003585428 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1943.2251608020015, |
|
"count": 1, |
|
"self": 1.474775712544215, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 13.508077049002168, |
|
"count": 1, |
|
"self": 13.508077049002168 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1928.159975061455, |
|
"count": 42957, |
|
"self": 1.15854264931113, |
|
"children": { |
|
"env_step": { |
|
"total": 477.5357708391384, |
|
"count": 42957, |
|
"self": 131.00419527236954, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 345.3808232630254, |
|
"count": 131887, |
|
"self": 8.298781538120238, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 337.08204172490514, |
|
"count": 125436, |
|
"self": 337.08204172490514 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.1507523037435021, |
|
"count": 42957, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 15537.698560449106, |
|
"count": 131883, |
|
"is_parallel": true, |
|
"self": 13232.392022320244, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00879246297699865, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0027776409406214952, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.006014822036377154, |
|
"count": 64, |
|
"is_parallel": true, |
|
"self": 0.006014822036377154 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.38589809798577335, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003574172980734147, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.002722707999055274, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002722707999055274 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.3683473840064835, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.3683473840064835 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.011253832999500446, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003931127008399926, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.00732270599110052, |
|
"count": 64, |
|
"is_parallel": true, |
|
"self": 0.00732270599110052 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2305.3065381288616, |
|
"count": 131875, |
|
"is_parallel": true, |
|
"self": 38.64903408114333, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 32.81288378901081, |
|
"count": 131875, |
|
"is_parallel": true, |
|
"self": 32.81288378901081 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2126.858278217769, |
|
"count": 131875, |
|
"is_parallel": true, |
|
"self": 2126.858278217769 |
|
}, |
|
"steps_from_proto": { |
|
"total": 106.98634204093833, |
|
"count": 131875, |
|
"is_parallel": true, |
|
"self": 26.78200793697033, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 80.204334103968, |
|
"count": 1055000, |
|
"is_parallel": true, |
|
"self": 80.204334103968 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1449.4656615730055, |
|
"count": 42957, |
|
"self": 3.6081198034225963, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 269.627192241649, |
|
"count": 42957, |
|
"self": 269.29844516263984, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3287470790091902, |
|
"count": 4, |
|
"self": 0.3287470790091902 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1176.2303495279339, |
|
"count": 935, |
|
"self": 592.5732438604755, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 583.6571056674584, |
|
"count": 45576, |
|
"self": 583.6571056674584 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 7.500057108700275e-07, |
|
"count": 1, |
|
"self": 7.500057108700275e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.08233222899434622, |
|
"count": 1, |
|
"self": 0.0014813790039625019, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08085084999038372, |
|
"count": 1, |
|
"self": 0.08085084999038372 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |