|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2625798285007477, |
|
"min": 0.2607177495956421, |
|
"max": 1.3998678922653198, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 7877.39501953125, |
|
"min": 7775.64599609375, |
|
"max": 42466.390625, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989913.0, |
|
"min": 29932.0, |
|
"max": 989913.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989913.0, |
|
"min": 29932.0, |
|
"max": 989913.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.4977078139781952, |
|
"min": -0.0600198395550251, |
|
"max": 0.5052624940872192, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 135.87423706054688, |
|
"min": -14.464781761169434, |
|
"max": 138.44192504882812, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.007753347512334585, |
|
"min": 0.006836325395852327, |
|
"max": 0.45998555421829224, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.116663932800293, |
|
"min": 1.8526442050933838, |
|
"max": 109.0165786743164, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06627495516513386, |
|
"min": 0.06535325211683791, |
|
"max": 0.07306322254204788, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9278493723118741, |
|
"min": 0.5703563344263127, |
|
"max": 1.0731484517261074, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.013768133272030308, |
|
"min": 0.0010384626681662326, |
|
"max": 0.014531300974004126, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.19275386580842432, |
|
"min": 0.010384626681662327, |
|
"max": 0.2124671098572435, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.755097415000004e-06, |
|
"min": 7.755097415000004e-06, |
|
"max": 0.00029484225171925, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010857136381000007, |
|
"min": 0.00010857136381000007, |
|
"max": 0.0037586596471134996, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.102585, |
|
"min": 0.102585, |
|
"max": 0.19828075, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4361899999999999, |
|
"min": 1.4361899999999999, |
|
"max": 2.6528864999999997, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002682415000000002, |
|
"min": 0.0002682415000000002, |
|
"max": 0.009828246924999999, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0037553810000000025, |
|
"min": 0.0037553810000000025, |
|
"max": 0.12530336135, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.01632445864379406, |
|
"min": 0.01632445864379406, |
|
"max": 0.626849889755249, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.22854243218898773, |
|
"min": 0.22854243218898773, |
|
"max": 5.014799118041992, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 378.2597402597403, |
|
"min": 358.6375, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29126.0, |
|
"min": 16475.0, |
|
"max": 33137.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.543802571567622, |
|
"min": -0.999962551984936, |
|
"max": 1.5913524799048901, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 118.8727980107069, |
|
"min": -31.998801663517952, |
|
"max": 128.13799849152565, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.543802571567622, |
|
"min": -0.999962551984936, |
|
"max": 1.5913524799048901, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 118.8727980107069, |
|
"min": -31.998801663517952, |
|
"max": 128.13799849152565, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.06365097203373594, |
|
"min": 0.06171568521094741, |
|
"max": 13.505366817993277, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.901124846597668, |
|
"min": 4.901124846597668, |
|
"max": 229.5912359058857, |
|
"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": "1691867756", |
|
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", |
|
"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 --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": "1691870086" |
|
}, |
|
"total": 2330.208787157, |
|
"count": 1, |
|
"self": 1.2918170580005608, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04828629399997908, |
|
"count": 1, |
|
"self": 0.04828629399997908 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2328.868683805, |
|
"count": 1, |
|
"self": 1.5938675000134026, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.207934155000032, |
|
"count": 1, |
|
"self": 4.207934155000032 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2322.9103810919864, |
|
"count": 63835, |
|
"self": 1.570508171045276, |
|
"children": { |
|
"env_step": { |
|
"total": 1641.6017569389714, |
|
"count": 63835, |
|
"self": 1522.630132676959, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 118.004710168021, |
|
"count": 63835, |
|
"self": 5.019106336018012, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 112.985603832003, |
|
"count": 62565, |
|
"self": 112.985603832003 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.9669140939915906, |
|
"count": 63835, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2322.956336398014, |
|
"count": 63835, |
|
"is_parallel": true, |
|
"self": 924.268317744089, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00531359199999315, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.001676427000120384, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003637164999872766, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003637164999872766 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.048281433999989076, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006129089999831194, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0006043180000006032, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006043180000006032 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.045143558999996, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.045143558999996 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019206480000093507, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000364677000050051, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015559709999592997, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015559709999592997 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1398.6880186539252, |
|
"count": 63834, |
|
"is_parallel": true, |
|
"self": 36.25195953189723, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.889131731024634, |
|
"count": 63834, |
|
"is_parallel": true, |
|
"self": 23.889131731024634 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1226.8439478869875, |
|
"count": 63834, |
|
"is_parallel": true, |
|
"self": 1226.8439478869875 |
|
}, |
|
"steps_from_proto": { |
|
"total": 111.70297950401584, |
|
"count": 63834, |
|
"is_parallel": true, |
|
"self": 22.488141032020053, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 89.21483847199579, |
|
"count": 510672, |
|
"is_parallel": true, |
|
"self": 89.21483847199579 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 679.7381159819695, |
|
"count": 63835, |
|
"self": 2.9424995349346545, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 114.1124499960365, |
|
"count": 63835, |
|
"self": 113.83373198203617, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2787180140003329, |
|
"count": 2, |
|
"self": 0.2787180140003329 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 562.6831664509983, |
|
"count": 457, |
|
"self": 366.1715978279793, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 196.511568623019, |
|
"count": 22770, |
|
"self": 196.511568623019 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.312999756919453e-06, |
|
"count": 1, |
|
"self": 1.312999756919453e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.15649974500001917, |
|
"count": 1, |
|
"self": 0.0035808800002996577, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.15291886499971952, |
|
"count": 1, |
|
"self": 0.15291886499971952 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |