|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.42549481987953186, |
|
"min": 0.4111776649951935, |
|
"max": 1.5053467750549316, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12730.8046875, |
|
"min": 12387.9609375, |
|
"max": 45666.19921875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989902.0, |
|
"min": 29952.0, |
|
"max": 989902.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989902.0, |
|
"min": 29952.0, |
|
"max": 989902.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.47972601652145386, |
|
"min": -0.10039714723825455, |
|
"max": 0.5392735004425049, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 131.92465209960938, |
|
"min": -23.794124603271484, |
|
"max": 148.83949279785156, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.01796160452067852, |
|
"min": -0.01796160452067852, |
|
"max": 0.2778169810771942, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -4.939441204071045, |
|
"min": -4.939441204071045, |
|
"max": 66.67607879638672, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06795589423854835, |
|
"min": 0.06505276952105175, |
|
"max": 0.07371888284786436, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0193384135782253, |
|
"min": 0.4793310039173263, |
|
"max": 1.0320643598701011, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017917507575798984, |
|
"min": 0.0005289067373441097, |
|
"max": 0.017917507575798984, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2687626136369848, |
|
"min": 0.007404694322817536, |
|
"max": 0.2687626136369848, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.560057480013335e-06, |
|
"min": 7.560057480013335e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011340086220020002, |
|
"min": 0.00011340086220020002, |
|
"max": 0.0035087099304300998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251998666666667, |
|
"min": 0.10251998666666667, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5377998000000002, |
|
"min": 1.3691136000000002, |
|
"max": 2.5695699000000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002617466680000001, |
|
"min": 0.0002617466680000001, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003926200020000001, |
|
"min": 0.003926200020000001, |
|
"max": 0.11698003301000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013938123360276222, |
|
"min": 0.013938123360276222, |
|
"max": 0.41634318232536316, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20907184481620789, |
|
"min": 0.1979716420173645, |
|
"max": 2.9144022464752197, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 373.90697674418607, |
|
"min": 348.74418604651163, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 32156.0, |
|
"min": 15984.0, |
|
"max": 32909.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5318282171207316, |
|
"min": -1.0000000521540642, |
|
"max": 1.5570571241634232, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 130.20539845526218, |
|
"min": -32.000001668930054, |
|
"max": 130.20539845526218, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5318282171207316, |
|
"min": -1.0000000521540642, |
|
"max": 1.5570571241634232, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 130.20539845526218, |
|
"min": -32.000001668930054, |
|
"max": 130.20539845526218, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05432191704167053, |
|
"min": 0.05383485282089718, |
|
"max": 8.619951163418591, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.617362948541995, |
|
"min": 4.21175814664457, |
|
"max": 137.91921861469746, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1679928554", |
|
"python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", |
|
"command_line_arguments": "/home/alertrack/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1679929722" |
|
}, |
|
"total": 1167.5940878670663, |
|
"count": 1, |
|
"self": 0.3194501604884863, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.015465166419744492, |
|
"count": 1, |
|
"self": 0.015465166419744492 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1167.259172540158, |
|
"count": 1, |
|
"self": 1.073605631943792, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 1.617504556197673, |
|
"count": 1, |
|
"self": 1.617504556197673 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1164.5068371659145, |
|
"count": 63657, |
|
"self": 1.0268876794725657, |
|
"children": { |
|
"env_step": { |
|
"total": 679.7438099337742, |
|
"count": 63657, |
|
"self": 619.4922338379547, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 59.567314818967134, |
|
"count": 63657, |
|
"self": 2.9170136274769902, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 56.65030119149014, |
|
"count": 62557, |
|
"self": 56.65030119149014 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6842612768523395, |
|
"count": 63657, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1165.7779096560553, |
|
"count": 63657, |
|
"is_parallel": true, |
|
"self": 616.9166472158395, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.001153741031885147, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003322213888168335, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0008215196430683136, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0008215196430683136 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.023083229083567858, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00021679094061255455, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00018640095368027687, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00018640095368027687 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.021926808170974255, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.021926808170974255 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0007532290183007717, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00017550308257341385, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0005777259357273579, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0005777259357273579 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 548.8612624402158, |
|
"count": 63656, |
|
"is_parallel": true, |
|
"self": 14.006551044993103, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 10.025138732045889, |
|
"count": 63656, |
|
"is_parallel": true, |
|
"self": 10.025138732045889 |
|
}, |
|
"communicator.exchange": { |
|
"total": 479.7300391192548, |
|
"count": 63656, |
|
"is_parallel": true, |
|
"self": 479.7300391192548 |
|
}, |
|
"steps_from_proto": { |
|
"total": 45.09953354392201, |
|
"count": 63656, |
|
"is_parallel": true, |
|
"self": 10.553896818310022, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.545636725611985, |
|
"count": 509248, |
|
"is_parallel": true, |
|
"self": 34.545636725611985 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 483.73613955266774, |
|
"count": 63657, |
|
"self": 1.8895969507284462, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 68.16445778124034, |
|
"count": 63657, |
|
"self": 67.97287175012752, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1915860311128199, |
|
"count": 2, |
|
"self": 0.1915860311128199 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 413.68208482069895, |
|
"count": 451, |
|
"self": 207.41235125390813, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 206.26973356679082, |
|
"count": 22806, |
|
"self": 206.26973356679082 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 9.289942681789398e-07, |
|
"count": 1, |
|
"self": 9.289942681789398e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.06122425710782409, |
|
"count": 1, |
|
"self": 0.0014217710122466087, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.05980248609557748, |
|
"count": 1, |
|
"self": 0.05980248609557748 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |