|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.3143894672393799, |
|
"min": 0.3018721044063568, |
|
"max": 1.5173466205596924, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9461.865234375, |
|
"min": 9089.97265625, |
|
"max": 46030.2265625, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 899946.0, |
|
"min": 29952.0, |
|
"max": 899946.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 899946.0, |
|
"min": 29952.0, |
|
"max": 899946.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5661607980728149, |
|
"min": -0.07692617923021317, |
|
"max": 0.6612709760665894, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 156.8265380859375, |
|
"min": -18.69306182861328, |
|
"max": 189.38992309570312, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0005080682458356023, |
|
"min": -0.020590951666235924, |
|
"max": 0.17304767668247223, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.14073491096496582, |
|
"min": -5.847830295562744, |
|
"max": 41.704490661621094, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0680910766488564, |
|
"min": 0.06459918983108807, |
|
"max": 0.07283377598440792, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9532750730839896, |
|
"min": 0.49954552701527205, |
|
"max": 1.0925066397661187, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014839827194575128, |
|
"min": 0.0007602584838577493, |
|
"max": 0.017616673432187074, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2077575807240518, |
|
"min": 0.006842326354719744, |
|
"max": 0.2642501014828061, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 5.024241182428572e-06, |
|
"min": 5.024241182428572e-06, |
|
"max": 0.000294611811319873, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 7.033937655400001e-05, |
|
"min": 7.033937655400001e-05, |
|
"max": 0.003448268817243777, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10167471428571428, |
|
"min": 0.10167471428571428, |
|
"max": 0.1982039365079365, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.423446, |
|
"min": 1.3874275555555555, |
|
"max": 2.544346777777778, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00017730395714285715, |
|
"min": 0.00017730395714285715, |
|
"max": 0.00982057325714286, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0024822554, |
|
"min": 0.0024822554, |
|
"max": 0.11495734660000001, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.010926744900643826, |
|
"min": 0.010926744900643826, |
|
"max": 0.36154836416244507, |
|
"count": 30 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1529744267463684, |
|
"min": 0.1529744267463684, |
|
"max": 2.5308384895324707, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 357.8, |
|
"min": 279.5904761904762, |
|
"max": 999.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30413.0, |
|
"min": 15984.0, |
|
"max": 32523.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6186611538424212, |
|
"min": -1.0000000521540642, |
|
"max": 1.7013561763933727, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 137.5861980766058, |
|
"min": -30.55440167337656, |
|
"max": 178.64239852130413, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6186611538424212, |
|
"min": -1.0000000521540642, |
|
"max": 1.7013561763933727, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 137.5861980766058, |
|
"min": -30.55440167337656, |
|
"max": 178.64239852130413, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0404436282477999, |
|
"min": 0.033162879603748606, |
|
"max": 7.883609194308519, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.4377084010629915, |
|
"min": 3.4377084010629915, |
|
"max": 126.13774710893631, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 30 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1663037986", |
|
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \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 --force", |
|
"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": "1663039910" |
|
}, |
|
"total": 1924.2608588920002, |
|
"count": 1, |
|
"self": 0.4412678379994759, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04964085200026602, |
|
"count": 1, |
|
"self": 0.04964085200026602 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1923.7699502020005, |
|
"count": 1, |
|
"self": 1.2086384270623967, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 5.598036690000299, |
|
"count": 1, |
|
"self": 5.598036690000299 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1916.8633218839377, |
|
"count": 57825, |
|
"self": 1.2712493989183713, |
|
"children": { |
|
"env_step": { |
|
"total": 1298.6090012799514, |
|
"count": 57825, |
|
"self": 1209.6398991310298, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 88.3406368768292, |
|
"count": 57825, |
|
"self": 4.105943385953651, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 84.23469349087554, |
|
"count": 56312, |
|
"self": 30.080371604844004, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 54.15432188603154, |
|
"count": 56312, |
|
"self": 54.15432188603154 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6284652720923987, |
|
"count": 57825, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1920.4270927631842, |
|
"count": 57825, |
|
"is_parallel": true, |
|
"self": 799.8686832981284, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019791639997492894, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007899419988461887, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011892220009031007, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011892220009031007 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04400810700008151, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005137100006322726, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004628869992302498, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004628869992302498 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04134547699959512, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04134547699959512 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016860330006238655, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003958099996452802, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012902230009785853, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012902230009785853 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1120.5584094650558, |
|
"count": 57824, |
|
"is_parallel": true, |
|
"self": 24.905355304088516, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 20.177002000952598, |
|
"count": 57824, |
|
"is_parallel": true, |
|
"self": 20.177002000952598 |
|
}, |
|
"communicator.exchange": { |
|
"total": 993.9248567621398, |
|
"count": 57824, |
|
"is_parallel": true, |
|
"self": 993.9248567621398 |
|
}, |
|
"steps_from_proto": { |
|
"total": 81.55119539787484, |
|
"count": 57824, |
|
"is_parallel": true, |
|
"self": 20.30215880967353, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 61.24903658820131, |
|
"count": 462592, |
|
"is_parallel": true, |
|
"self": 61.24903658820131 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 616.983071205068, |
|
"count": 57825, |
|
"self": 2.2400394880751264, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 139.49717225100903, |
|
"count": 57825, |
|
"self": 139.38434084000892, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11283141100011562, |
|
"count": 1, |
|
"self": 0.11283141100011562 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 475.2458594659838, |
|
"count": 405, |
|
"self": 190.12632660298823, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 285.1195328629956, |
|
"count": 20529, |
|
"self": 285.1195328629956 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1410002116463147e-06, |
|
"count": 1, |
|
"self": 1.1410002116463147e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09995205999985046, |
|
"count": 1, |
|
"self": 0.0020695530001830775, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09788250699966738, |
|
"count": 1, |
|
"self": 0.09788250699966738 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |