|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.6862469911575317, |
|
"min": 0.6862469911575317, |
|
"max": 1.412160038948059, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 20554.470703125, |
|
"min": 20554.470703125, |
|
"max": 42839.28515625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479902.0, |
|
"min": 29952.0, |
|
"max": 479902.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479902.0, |
|
"min": 29952.0, |
|
"max": 479902.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.043696556240320206, |
|
"min": -0.11794018745422363, |
|
"max": -0.029356027022004128, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -10.53087043762207, |
|
"min": -28.659465789794922, |
|
"max": -6.957378387451172, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.034689053893089294, |
|
"min": 0.023891914635896683, |
|
"max": 0.49538207054138184, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 8.360061645507812, |
|
"min": 5.7340593338012695, |
|
"max": 117.40554809570312, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0688603321515974, |
|
"min": 0.0651057852697958, |
|
"max": 0.07289142580433874, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9640446501223635, |
|
"min": 0.4828183464833064, |
|
"max": 1.0204799612607425, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.002170354041003602, |
|
"min": 0.00017892138657097317, |
|
"max": 0.0076368311433971875, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.03038495657405043, |
|
"min": 0.002325978025422651, |
|
"max": 0.05485889393251044, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.096975015297143e-05, |
|
"min": 2.096975015297143e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029357650214160004, |
|
"min": 0.00029357650214160004, |
|
"max": 0.0033182419939194003, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10698988571428569, |
|
"min": 0.10698988571428569, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4978583999999997, |
|
"min": 1.3773696000000002, |
|
"max": 2.4224856000000003, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007082895828571429, |
|
"min": 0.0007082895828571429, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009916054160000002, |
|
"min": 0.009916054160000002, |
|
"max": 0.11062745194, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.023987699300050735, |
|
"min": 0.023987699300050735, |
|
"max": 0.4914165139198303, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.3358277976512909, |
|
"min": 0.3358277976512909, |
|
"max": 3.439915657043457, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 976.6451612903226, |
|
"min": 906.6363636363636, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30276.0, |
|
"min": 15984.0, |
|
"max": 32465.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.6545290850823925, |
|
"min": -1.0000000521540642, |
|
"max": -0.4222242884112127, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -20.29040163755417, |
|
"min": -31.992401644587517, |
|
"max": -13.933401517570019, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.6545290850823925, |
|
"min": -1.0000000521540642, |
|
"max": -0.4222242884112127, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -20.29040163755417, |
|
"min": -31.992401644587517, |
|
"max": -13.933401517570019, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.23917870455601764, |
|
"min": 0.2368117618007642, |
|
"max": 9.578871441073716, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.414539841236547, |
|
"min": 7.414539841236547, |
|
"max": 153.26194305717945, |
|
"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": "1658511186", |
|
"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": "1658512173" |
|
}, |
|
"total": 987.0061175570002, |
|
"count": 1, |
|
"self": 0.4839275640002825, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04233199399993737, |
|
"count": 1, |
|
"self": 0.04233199399993737 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 986.4798579989999, |
|
"count": 1, |
|
"self": 0.7051505339910591, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 9.283431921000101, |
|
"count": 1, |
|
"self": 9.283431921000101 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 976.3964635390088, |
|
"count": 31589, |
|
"self": 0.7438110289948554, |
|
"children": { |
|
"env_step": { |
|
"total": 607.2333256690127, |
|
"count": 31589, |
|
"self": 551.3323171290245, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 55.51560935600742, |
|
"count": 31589, |
|
"self": 2.3960192740006505, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 53.119590082006766, |
|
"count": 31315, |
|
"self": 18.076592242019046, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 35.04299783998772, |
|
"count": 31315, |
|
"self": 35.04299783998772 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.38539918398078044, |
|
"count": 31589, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 984.2733045910014, |
|
"count": 31589, |
|
"is_parallel": true, |
|
"self": 484.98025382802155, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006300643000031414, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004936916000019664, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013637270000117496, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013637270000117496 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04461161400001856, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00048283399996762455, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00045131400008813216, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00045131400008813216 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04208954399996401, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04208954399996401 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015879219999987981, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004250099999580925, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011629120000407056, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011629120000407056 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 499.2930507629799, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 14.210155919980025, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.018304755014583, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 12.018304755014583 |
|
}, |
|
"communicator.exchange": { |
|
"total": 424.94029096798727, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 424.94029096798727 |
|
}, |
|
"steps_from_proto": { |
|
"total": 48.124299119998, |
|
"count": 31588, |
|
"is_parallel": true, |
|
"self": 11.99372052398246, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 36.13057859601554, |
|
"count": 252704, |
|
"is_parallel": true, |
|
"self": 36.13057859601554 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 368.4193268410012, |
|
"count": 31589, |
|
"self": 1.2559131539493364, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 84.08955183004991, |
|
"count": 31589, |
|
"self": 83.97182682604989, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11772500400002173, |
|
"count": 1, |
|
"self": 0.11772500400002173 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 283.07386185700193, |
|
"count": 217, |
|
"self": 109.91755481000212, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 173.1563070469998, |
|
"count": 11400, |
|
"self": 173.1563070469998 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0450000900164014e-06, |
|
"count": 1, |
|
"self": 1.0450000900164014e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.0948109599999043, |
|
"count": 1, |
|
"self": 0.0015478959999200015, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0932630639999843, |
|
"count": 1, |
|
"self": 0.0932630639999843 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |