|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.36755046248435974, |
|
"min": 0.35287874937057495, |
|
"max": 1.4512220621109009, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 11067.6796875, |
|
"min": 10541.1943359375, |
|
"max": 44024.2734375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989924.0, |
|
"min": 29952.0, |
|
"max": 989924.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989924.0, |
|
"min": 29952.0, |
|
"max": 989924.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.6756559610366821, |
|
"min": -0.10665462911128998, |
|
"max": 0.6876348853111267, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 193.9132537841797, |
|
"min": -25.703765869140625, |
|
"max": 200.10174560546875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.014521007426083088, |
|
"min": -0.03204679861664772, |
|
"max": 0.28865253925323486, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.167529106140137, |
|
"min": -8.65263557434082, |
|
"max": 69.85391235351562, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06820287926060152, |
|
"min": 0.06528136473137973, |
|
"max": 0.07377216319478716, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0230431889090228, |
|
"min": 0.5124505107072262, |
|
"max": 1.0679575363950184, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01657163596307262, |
|
"min": 0.000674331314588271, |
|
"max": 0.01657163596307262, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.24857453944608932, |
|
"min": 0.007417644460470982, |
|
"max": 0.24857453944608932, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.506097498000003e-06, |
|
"min": 7.506097498000003e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011259146247000003, |
|
"min": 0.00011259146247000003, |
|
"max": 0.0035072978309007995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10250200000000001, |
|
"min": 0.10250200000000001, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.53753, |
|
"min": 1.3886848, |
|
"max": 2.5690992, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002599498, |
|
"min": 0.0002599498, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003899247, |
|
"min": 0.003899247, |
|
"max": 0.11693301008000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013412834145128727, |
|
"min": 0.013065861538052559, |
|
"max": 0.5309029817581177, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.20119251310825348, |
|
"min": 0.18292206525802612, |
|
"max": 3.716320753097534, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 287.43809523809523, |
|
"min": 272.4954128440367, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30181.0, |
|
"min": 15984.0, |
|
"max": 33192.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6744628466310956, |
|
"min": -1.0000000521540642, |
|
"max": 1.7177744864248763, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 175.81859889626503, |
|
"min": -30.99840161204338, |
|
"max": 184.2959993928671, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6744628466310956, |
|
"min": -1.0000000521540642, |
|
"max": 1.7177744864248763, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 175.81859889626503, |
|
"min": -30.99840161204338, |
|
"max": 184.2959993928671, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.03998106409923085, |
|
"min": 0.03762781582177305, |
|
"max": 11.067019287496805, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.198011730419239, |
|
"min": 3.9282846567657543, |
|
"max": 177.07230859994888, |
|
"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": "1673392468", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"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", |
|
"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": "1673394627" |
|
}, |
|
"total": 2159.0256026630004, |
|
"count": 1, |
|
"self": 0.47493200400003843, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.10920643600002222, |
|
"count": 1, |
|
"self": 0.10920643600002222 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2158.4414642230004, |
|
"count": 1, |
|
"self": 1.2843140039908576, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.226269484000113, |
|
"count": 1, |
|
"self": 6.226269484000113 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2150.8383515620094, |
|
"count": 64072, |
|
"self": 1.3886537209814378, |
|
"children": { |
|
"env_step": { |
|
"total": 1476.5336190150024, |
|
"count": 64072, |
|
"self": 1369.6151597531095, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 106.09519231798186, |
|
"count": 64072, |
|
"self": 4.474340670990159, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 101.6208516469917, |
|
"count": 62557, |
|
"self": 34.35173498897666, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 67.26911665801504, |
|
"count": 62557, |
|
"self": 67.26911665801504 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.8232669439109941, |
|
"count": 64072, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2153.8866914300684, |
|
"count": 64072, |
|
"is_parallel": true, |
|
"self": 887.4396241640948, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00180794099992454, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006408079996162996, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011671330003082403, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011671330003082403 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04441180300000269, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005322220001744427, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004944590000377502, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004944590000377502 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0416750869999305, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0416750869999305 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017100349998599995, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004311819993745303, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012788530004854692, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012788530004854692 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1266.4470672659736, |
|
"count": 64071, |
|
"is_parallel": true, |
|
"self": 28.510432608087058, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 24.215833447909063, |
|
"count": 64071, |
|
"is_parallel": true, |
|
"self": 24.215833447909063 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1105.7518920369307, |
|
"count": 64071, |
|
"is_parallel": true, |
|
"self": 1105.7518920369307 |
|
}, |
|
"steps_from_proto": { |
|
"total": 107.96890917304677, |
|
"count": 64071, |
|
"is_parallel": true, |
|
"self": 23.60536206608913, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 84.36354710695764, |
|
"count": 512568, |
|
"is_parallel": true, |
|
"self": 84.36354710695764 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 672.9160788260256, |
|
"count": 64072, |
|
"self": 2.3950769599964588, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 154.1069868980362, |
|
"count": 64072, |
|
"self": 153.90240413503625, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20458276299996214, |
|
"count": 2, |
|
"self": 0.20458276299996214 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 516.4140149679929, |
|
"count": 449, |
|
"self": 202.3677294590184, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 314.0462855089745, |
|
"count": 22770, |
|
"self": 314.0462855089745 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.4689999261463527e-06, |
|
"count": 1, |
|
"self": 1.4689999261463527e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09252770400007648, |
|
"count": 1, |
|
"self": 0.0013933690001977084, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09113433499987877, |
|
"count": 1, |
|
"self": 0.09113433499987877 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |