|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.4205172061920166, |
|
"min": 0.4205172061920166, |
|
"max": 1.178979754447937, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 12689.52734375, |
|
"min": 12689.52734375, |
|
"max": 34186.8125, |
|
"count": 31 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989915.0, |
|
"min": 89998.0, |
|
"max": 989915.0, |
|
"count": 31 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989915.0, |
|
"min": 89998.0, |
|
"max": 989915.0, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.578375518321991, |
|
"min": -0.09325366467237473, |
|
"max": 0.6088351607322693, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 160.21002197265625, |
|
"min": -22.38088035583496, |
|
"max": 171.08267211914062, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.15920183062553406, |
|
"min": -0.15920183062553406, |
|
"max": 0.12669534981250763, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -44.098907470703125, |
|
"min": -44.098907470703125, |
|
"max": 25.567962646484375, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06781885955909578, |
|
"min": 0.06377447864118342, |
|
"max": 0.07362295601892078, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0172828933864366, |
|
"min": 0.14013763737845392, |
|
"max": 1.1043443402838118, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.020172474435659955, |
|
"min": 0.0003241572943200784, |
|
"max": 0.020172474435659955, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.30258711653489934, |
|
"min": 0.0006483145886401568, |
|
"max": 0.30258711653489934, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.5422774859400034e-06, |
|
"min": 7.5422774859400034e-06, |
|
"max": 0.00027422940859020005, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00011313416228910005, |
|
"min": 0.00011313416228910005, |
|
"max": 0.0031372469542511002, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10251405999999999, |
|
"min": 0.10251405999999999, |
|
"max": 0.19140980000000005, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5377108999999998, |
|
"min": 0.3828196000000001, |
|
"max": 2.4437612, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002611545940000001, |
|
"min": 0.0002611545940000001, |
|
"max": 0.00914183902, |
|
"count": 31 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.003917318910000002, |
|
"min": 0.003917318910000002, |
|
"max": 0.10460031511, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.008740575052797794, |
|
"min": 0.008740575052797794, |
|
"max": 0.09000152349472046, |
|
"count": 31 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1311086267232895, |
|
"min": 0.12701763212680817, |
|
"max": 0.6430901288986206, |
|
"count": 31 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 31 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 31 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 326.6923076923077, |
|
"min": 312.42105263157896, |
|
"max": 999.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29729.0, |
|
"min": 25036.0, |
|
"max": 33299.0, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.6293362414280137, |
|
"min": -0.9999806977087452, |
|
"max": 1.6875789339605132, |
|
"count": 30 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 148.26959796994925, |
|
"min": -30.9994016289711, |
|
"max": 160.31999872624874, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.6293362414280137, |
|
"min": -0.9999806977087452, |
|
"max": 1.6875789339605132, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 148.26959796994925, |
|
"min": -30.9994016289711, |
|
"max": 160.31999872624874, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.02928505246373978, |
|
"min": 0.02928505246373978, |
|
"max": 0.7404885896591141, |
|
"count": 30 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.6649397742003202, |
|
"min": 2.6649397742003202, |
|
"max": 25.17661204840988, |
|
"count": 30 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1677351631", |
|
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", |
|
"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 --resume", |
|
"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": "1.22.4", |
|
"end_time_seconds": "1677353799" |
|
}, |
|
"total": 2168.03837705, |
|
"count": 1, |
|
"self": 0.5264525419997881, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11523128399994675, |
|
"count": 1, |
|
"self": 0.11523128399994675 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2167.396693224, |
|
"count": 1, |
|
"self": 1.281207674162033, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 7.431841023999823, |
|
"count": 1, |
|
"self": 7.431841023999823 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2158.5916747428387, |
|
"count": 58930, |
|
"self": 1.4100693748250706, |
|
"children": { |
|
"env_step": { |
|
"total": 1451.608715427868, |
|
"count": 58930, |
|
"self": 1345.1334192078716, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 105.7063820859039, |
|
"count": 58930, |
|
"self": 4.455333714709013, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 101.25104837119488, |
|
"count": 57563, |
|
"self": 34.654481669223514, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 66.59656670197137, |
|
"count": 57563, |
|
"self": 66.59656670197137 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.7689141340924834, |
|
"count": 58930, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2162.7388273921424, |
|
"count": 58930, |
|
"is_parallel": true, |
|
"self": 925.3624172811874, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0027587790000325185, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0009597249995749735, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001799054000457545, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001799054000457545 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.048602867999761656, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005728439996346424, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005117810001138423, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005117810001138423 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.045841995000046154, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.045841995000046154 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016762479999670177, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00043473300047480734, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012415149994922103, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012415149994922103 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1237.376410110955, |
|
"count": 58929, |
|
"is_parallel": true, |
|
"self": 29.76034144775622, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 22.040904430164574, |
|
"count": 58929, |
|
"is_parallel": true, |
|
"self": 22.040904430164574 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1098.0368322140225, |
|
"count": 58929, |
|
"is_parallel": true, |
|
"self": 1098.0368322140225 |
|
}, |
|
"steps_from_proto": { |
|
"total": 87.5383320190117, |
|
"count": 58929, |
|
"is_parallel": true, |
|
"self": 20.82721406836481, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 66.7111179506469, |
|
"count": 471432, |
|
"is_parallel": true, |
|
"self": 66.7111179506469 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 705.5728899401456, |
|
"count": 58930, |
|
"self": 2.4748141240802397, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 157.126547701062, |
|
"count": 58930, |
|
"self": 156.86858836006286, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.2579593409991503, |
|
"count": 2, |
|
"self": 0.2579593409991503 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 545.9715281150034, |
|
"count": 421, |
|
"self": 212.2055353260048, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 333.7659927889986, |
|
"count": 20955, |
|
"self": 333.7659927889986 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0199992175330408e-06, |
|
"count": 1, |
|
"self": 1.0199992175330408e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09196876300029544, |
|
"count": 1, |
|
"self": 0.0019856570006595575, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.08998310599963588, |
|
"count": 1, |
|
"self": 0.08998310599963588 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |