|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.8169429898262024, |
|
"min": 0.806969165802002, |
|
"max": 1.4370100498199463, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 24469.076171875, |
|
"min": 24234.8984375, |
|
"max": 43593.13671875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479940.0, |
|
"min": 29952.0, |
|
"max": 479940.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479940.0, |
|
"min": 29952.0, |
|
"max": 479940.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.04986242949962616, |
|
"min": -0.15822254121303558, |
|
"max": 0.04986242949962616, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 12.316020011901855, |
|
"min": -37.498741149902344, |
|
"max": 12.316020011901855, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.010365001857280731, |
|
"min": 0.010365001857280731, |
|
"max": 0.34018850326538086, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.5601553916931152, |
|
"min": 2.5601553916931152, |
|
"max": 80.62467193603516, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07044651500819739, |
|
"min": 0.06684678239791, |
|
"max": 0.0724389859115289, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9862512101147634, |
|
"min": 0.48608461938378256, |
|
"max": 1.0065559870403662, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.006891457082842646, |
|
"min": 0.0002047633932934106, |
|
"max": 0.006891457082842646, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.09648039915979705, |
|
"min": 0.0022523973262275165, |
|
"max": 0.09648039915979705, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.104787869835714e-05, |
|
"min": 2.104787869835714e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029467030177699995, |
|
"min": 0.00029467030177699995, |
|
"max": 0.0030613525795492, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10701592857142858, |
|
"min": 0.10701592857142858, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.498223, |
|
"min": 1.3773696000000002, |
|
"max": 2.338242, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007108912642857145, |
|
"min": 0.0007108912642857145, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009952477700000002, |
|
"min": 0.009952477700000002, |
|
"max": 0.10206303491999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.016652943566441536, |
|
"min": 0.016652943566441536, |
|
"max": 0.2874681055545807, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.2331411987543106, |
|
"min": 0.2331411987543106, |
|
"max": 2.0122766494750977, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 788.5, |
|
"min": 788.5, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28386.0, |
|
"min": 15984.0, |
|
"max": 32485.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.21122774129940403, |
|
"min": -1.0000000521540642, |
|
"max": 0.21122774129940403, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 7.604198686778545, |
|
"min": -31.99920167028904, |
|
"max": 7.604198686778545, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.21122774129940403, |
|
"min": -1.0000000521540642, |
|
"max": 0.21122774129940403, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 7.604198686778545, |
|
"min": -31.99920167028904, |
|
"max": 7.604198686778545, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.13601157856788226, |
|
"min": 0.13601157856788226, |
|
"max": 5.298088546842337, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.896416828443762, |
|
"min": 4.896416828443762, |
|
"max": 84.76941674947739, |
|
"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": "1658302366", |
|
"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", |
|
"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": "1658303644" |
|
}, |
|
"total": 1278.1808403619998, |
|
"count": 1, |
|
"self": 0.5433971499999188, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04995043399998167, |
|
"count": 1, |
|
"self": 0.04995043399998167 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1277.5874927779998, |
|
"count": 1, |
|
"self": 1.100050795013658, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.867765102000021, |
|
"count": 1, |
|
"self": 11.867765102000021 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1264.5073676609861, |
|
"count": 31569, |
|
"self": 1.224909814977309, |
|
"children": { |
|
"env_step": { |
|
"total": 837.1348374540222, |
|
"count": 31569, |
|
"self": 759.5768583050055, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 76.9726208750007, |
|
"count": 31569, |
|
"self": 3.096678221994523, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 73.87594265300618, |
|
"count": 31314, |
|
"self": 24.900829790007094, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 48.97511286299908, |
|
"count": 31314, |
|
"self": 48.97511286299908 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.5853582740160164, |
|
"count": 31569, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1274.8497632750054, |
|
"count": 31569, |
|
"is_parallel": true, |
|
"self": 584.9230296140405, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.005344230999980937, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.003953152999940812, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013910780000401246, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013910780000401246 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06146187199999531, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006461890000650783, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000527735999980905, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000527735999980905 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05796244499998693, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05796244499998693 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0023255019999623983, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005187510000723705, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0018067509998900277, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0018067509998900277 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 689.9267336609649, |
|
"count": 31568, |
|
"is_parallel": true, |
|
"self": 19.040213349004148, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 14.625543335003726, |
|
"count": 31568, |
|
"is_parallel": true, |
|
"self": 14.625543335003726 |
|
}, |
|
"communicator.exchange": { |
|
"total": 597.562182493971, |
|
"count": 31568, |
|
"is_parallel": true, |
|
"self": 597.562182493971 |
|
}, |
|
"steps_from_proto": { |
|
"total": 58.6987944829861, |
|
"count": 31568, |
|
"is_parallel": true, |
|
"self": 15.45118869398192, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 43.24760578900418, |
|
"count": 252544, |
|
"is_parallel": true, |
|
"self": 43.24760578900418 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 426.1476203919866, |
|
"count": 31569, |
|
"self": 1.8935426410019431, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 95.29461102898443, |
|
"count": 31569, |
|
"self": 95.17260518098459, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12200584799984426, |
|
"count": 1, |
|
"self": 0.12200584799984426 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 328.95946672200023, |
|
"count": 214, |
|
"self": 126.30239331998598, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 202.65707340201425, |
|
"count": 11436, |
|
"self": 202.65707340201425 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.1859999631269602e-06, |
|
"count": 1, |
|
"self": 1.1859999631269602e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11230803400007972, |
|
"count": 1, |
|
"self": 0.001862529000163704, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11044550499991601, |
|
"count": 1, |
|
"self": 0.11044550499991601 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |