|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1734270453453064, |
|
"min": 0.1626211553812027, |
|
"max": 1.4498789310455322, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5169.51318359375, |
|
"min": 4889.2529296875, |
|
"max": 43983.52734375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999902.0, |
|
"min": 29952.0, |
|
"max": 2999902.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999902.0, |
|
"min": 29952.0, |
|
"max": 2999902.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.754357635974884, |
|
"min": -0.1312602460384369, |
|
"max": 0.8611552119255066, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 215.74627685546875, |
|
"min": -31.63372039794922, |
|
"max": 254.04078674316406, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0033349106088280678, |
|
"min": -0.014645138755440712, |
|
"max": 0.4561350345611572, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 0.9537844061851501, |
|
"min": -4.085993766784668, |
|
"max": 108.10400390625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06716880165151365, |
|
"min": 0.06485454586800188, |
|
"max": 0.07454089974219513, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9403632231211911, |
|
"min": 0.5034031208518266, |
|
"max": 1.1092770241472558, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014674293200230403, |
|
"min": 0.00012045676588491576, |
|
"max": 0.017596050165145247, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20544010480322564, |
|
"min": 0.0013250244247340734, |
|
"max": 0.24634470231203345, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5148352093738128e-06, |
|
"min": 1.5148352093738128e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.120769293123338e-05, |
|
"min": 2.120769293123338e-05, |
|
"max": 0.003842999019000367, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050491190476189, |
|
"min": 0.10050491190476189, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4070687666666666, |
|
"min": 1.3962282666666668, |
|
"max": 2.7526058666666673, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.0440699285714394e-05, |
|
"min": 6.0440699285714394e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008461697900000015, |
|
"min": 0.0008461697900000015, |
|
"max": 0.12811186337, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006210089195519686, |
|
"min": 0.00600480055436492, |
|
"max": 0.4624593257904053, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.08694124966859818, |
|
"min": 0.0840672105550766, |
|
"max": 3.237215280532837, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 249.6206896551724, |
|
"min": 215.81617647058823, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 28956.0, |
|
"min": 15984.0, |
|
"max": 32956.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7331344703661984, |
|
"min": -1.0000000521540642, |
|
"max": 1.7848393979081272, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 201.04359856247902, |
|
"min": -31.998401656746864, |
|
"max": 244.52299751341343, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7331344703661984, |
|
"min": -1.0000000521540642, |
|
"max": 1.7848393979081272, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 201.04359856247902, |
|
"min": -31.998401656746864, |
|
"max": 244.52299751341343, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.016095047999097632, |
|
"min": 0.01404887657708371, |
|
"max": 9.761986959725618, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 1.8670255678953254, |
|
"min": 1.8072425858408678, |
|
"max": 156.1917913556099, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 100 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1690354683", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"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": "1690362385" |
|
}, |
|
"total": 7702.065467801, |
|
"count": 1, |
|
"self": 0.5471468510004343, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.03324788100007936, |
|
"count": 1, |
|
"self": 0.03324788100007936 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7701.485073069, |
|
"count": 1, |
|
"self": 4.7972480500566235, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.037148493999894, |
|
"count": 1, |
|
"self": 4.037148493999894 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7692.552408370942, |
|
"count": 194379, |
|
"self": 4.94181317370203, |
|
"children": { |
|
"env_step": { |
|
"total": 5680.920608533129, |
|
"count": 194379, |
|
"self": 5326.844493499253, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 351.15077393709817, |
|
"count": 194379, |
|
"self": 15.398563165106907, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 335.75221077199126, |
|
"count": 187544, |
|
"self": 335.75221077199126 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.9253410967780837, |
|
"count": 194379, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7684.347814948146, |
|
"count": 194379, |
|
"is_parallel": true, |
|
"self": 2736.9356454742547, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0017692420001367282, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005972090000341268, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011720330001026014, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011720330001026014 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.061581990000149744, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006242239999210142, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005231170000570273, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005231170000570273 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05846220800003721, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05846220800003721 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001972441000134495, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042134700015594717, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015510939999785478, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015510939999785478 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4947.4121694738915, |
|
"count": 194378, |
|
"is_parallel": true, |
|
"self": 108.66524012065747, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 75.00519569890798, |
|
"count": 194378, |
|
"is_parallel": true, |
|
"self": 75.00519569890798 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4424.297072127102, |
|
"count": 194378, |
|
"is_parallel": true, |
|
"self": 4424.297072127102 |
|
}, |
|
"steps_from_proto": { |
|
"total": 339.4446615272234, |
|
"count": 194378, |
|
"is_parallel": true, |
|
"self": 71.08098363265844, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 268.36367789456494, |
|
"count": 1555024, |
|
"is_parallel": true, |
|
"self": 268.36367789456494 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2006.6899866641118, |
|
"count": 194379, |
|
"self": 8.958932142950516, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 363.22435207617036, |
|
"count": 194379, |
|
"self": 362.4030286361708, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8213234399995599, |
|
"count": 6, |
|
"self": 0.8213234399995599 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1634.5067024449909, |
|
"count": 1388, |
|
"self": 1069.7402425051293, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 564.7664599398615, |
|
"count": 68394, |
|
"self": 564.7664599398615 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0170006135012954e-06, |
|
"count": 1, |
|
"self": 1.0170006135012954e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09826713700022083, |
|
"count": 1, |
|
"self": 0.0014133509994280757, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09685378600079275, |
|
"count": 1, |
|
"self": 0.09685378600079275 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |