|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.31846192479133606, |
|
"min": 0.31712907552719116, |
|
"max": 1.380419373512268, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 9528.380859375, |
|
"min": 9528.380859375, |
|
"max": 41876.40234375, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989928.0, |
|
"min": 29952.0, |
|
"max": 989928.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989928.0, |
|
"min": 29952.0, |
|
"max": 989928.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5974531769752502, |
|
"min": -0.1484963595867157, |
|
"max": 0.5992048382759094, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 166.68943786621094, |
|
"min": -35.78762435913086, |
|
"max": 168.37655639648438, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.01993049681186676, |
|
"min": 0.003600776195526123, |
|
"max": 0.5776336193084717, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.560608863830566, |
|
"min": 0.936201810836792, |
|
"max": 136.899169921875, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07101942357465824, |
|
"min": 0.06457643765800943, |
|
"max": 0.07451330850757995, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9942719300452153, |
|
"min": 0.5215931595530596, |
|
"max": 1.0263331604849857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01761896005302246, |
|
"min": 0.0007128264535664507, |
|
"max": 0.01771979556584937, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.24666544074231447, |
|
"min": 0.009266743896363859, |
|
"max": 0.24807713792189118, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.331540413328571e-06, |
|
"min": 7.331540413328571e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001026415657866, |
|
"min": 0.0001026415657866, |
|
"max": 0.0035079959306680993, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10244381428571428, |
|
"min": 0.10244381428571428, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4342134, |
|
"min": 1.3886848, |
|
"max": 2.569331900000001, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025413704714285715, |
|
"min": 0.00025413704714285715, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00355791866, |
|
"min": 0.00355791866, |
|
"max": 0.11695625680999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.016155779361724854, |
|
"min": 0.016155779361724854, |
|
"max": 0.6117459535598755, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.22618091106414795, |
|
"min": 0.22618091106414795, |
|
"max": 4.282221794128418, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 324.1530612244898, |
|
"min": 306.96875, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31767.0, |
|
"min": 15984.0, |
|
"max": 33079.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.655430595333479, |
|
"min": -1.0000000521540642, |
|
"max": 1.655430595333479, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 162.23219834268093, |
|
"min": -30.730001732707024, |
|
"max": 162.23219834268093, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.655430595333479, |
|
"min": -1.0000000521540642, |
|
"max": 1.655430595333479, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 162.23219834268093, |
|
"min": -30.730001732707024, |
|
"max": 162.23219834268093, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.05385339676404885, |
|
"min": 0.05242809605503377, |
|
"max": 12.16811584867537, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 5.277632882876787, |
|
"min": 4.855591664090753, |
|
"max": 194.68985357880592, |
|
"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": "1686556903", |
|
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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", |
|
"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": "1686559229" |
|
}, |
|
"total": 2325.9307431629995, |
|
"count": 1, |
|
"self": 0.43891532299949176, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04168815100001666, |
|
"count": 1, |
|
"self": 0.04168815100001666 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2325.450139689, |
|
"count": 1, |
|
"self": 1.6588341330548246, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.208752058999835, |
|
"count": 1, |
|
"self": 4.208752058999835 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2319.487763813945, |
|
"count": 63853, |
|
"self": 1.6362681219602564, |
|
"children": { |
|
"env_step": { |
|
"total": 1657.7779834429743, |
|
"count": 63853, |
|
"self": 1531.9953808459175, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 124.7582864710239, |
|
"count": 63853, |
|
"self": 5.141384641045306, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 119.61690182997859, |
|
"count": 62556, |
|
"self": 119.61690182997859 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.0243161260329998, |
|
"count": 63853, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2319.581137104038, |
|
"count": 63853, |
|
"is_parallel": true, |
|
"self": 913.2930507030565, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019038820000787382, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005755860001954716, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013282959998832666, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013282959998832666 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05056612099997437, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005523979998542927, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0004768680000779568, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004768680000779568 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.047670763000041916, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.047670763000041916 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001866092000000208, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0003802499995799735, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014858420004202344, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014858420004202344 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1406.2880864009817, |
|
"count": 63852, |
|
"is_parallel": true, |
|
"self": 34.90020701278331, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.164081639086817, |
|
"count": 63852, |
|
"is_parallel": true, |
|
"self": 23.164081639086817 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1241.7657896400524, |
|
"count": 63852, |
|
"is_parallel": true, |
|
"self": 1241.7657896400524 |
|
}, |
|
"steps_from_proto": { |
|
"total": 106.45800810905916, |
|
"count": 63852, |
|
"is_parallel": true, |
|
"self": 21.50874675705336, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 84.9492613520058, |
|
"count": 510816, |
|
"is_parallel": true, |
|
"self": 84.9492613520058 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 660.0735122490105, |
|
"count": 63853, |
|
"self": 3.0032061210431493, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 113.14352601996484, |
|
"count": 63853, |
|
"self": 112.93943343296428, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20409258700055943, |
|
"count": 2, |
|
"self": 0.20409258700055943 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 543.9267801080025, |
|
"count": 450, |
|
"self": 346.762305897053, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 197.1644742109495, |
|
"count": 22845, |
|
"self": 197.1644742109495 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0739995559561066e-06, |
|
"count": 1, |
|
"self": 1.0739995559561066e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09478860900071595, |
|
"count": 1, |
|
"self": 0.0013730960008615511, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.0934155129998544, |
|
"count": 1, |
|
"self": 0.0934155129998544 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |