|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.15511548519134521, |
|
"min": 0.15511548519134521, |
|
"max": 1.4716479778289795, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 4675.80126953125, |
|
"min": 4643.11865234375, |
|
"max": 44643.9140625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999895.0, |
|
"min": 29937.0, |
|
"max": 2999895.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999895.0, |
|
"min": 29937.0, |
|
"max": 2999895.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7782980799674988, |
|
"min": -0.15698327124118805, |
|
"max": 0.848103404045105, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 229.59793090820312, |
|
"min": -37.67598342895508, |
|
"max": 260.36773681640625, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.013671457767486572, |
|
"min": -0.0007952329469844699, |
|
"max": 0.46688979864120483, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 4.033080101013184, |
|
"min": -0.2322080135345459, |
|
"max": 111.1197738647461, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07030294589224338, |
|
"min": 0.064918372890527, |
|
"max": 0.07359794507404635, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9842412424914073, |
|
"min": 0.6239968793067233, |
|
"max": 1.0878066654338767, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015881834198288352, |
|
"min": 0.00017079232478792224, |
|
"max": 0.01711644900161173, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.22234567877603692, |
|
"min": 0.0023910925470309115, |
|
"max": 0.24227163909852284, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4840852196238058e-06, |
|
"min": 1.4840852196238058e-06, |
|
"max": 0.00029826734502199633, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.0777193074733282e-05, |
|
"min": 2.0777193074733282e-05, |
|
"max": 0.004011188262937266, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049466190476188, |
|
"min": 0.10049466190476188, |
|
"max": 0.1994224481481482, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4069252666666663, |
|
"min": 1.4069252666666663, |
|
"max": 2.7370627333333335, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.9416724285714176e-05, |
|
"min": 5.9416724285714176e-05, |
|
"max": 0.009942302569999999, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008318341399999985, |
|
"min": 0.0008318341399999985, |
|
"max": 0.13371256705999998, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.006480519659817219, |
|
"min": 0.006480519659817219, |
|
"max": 0.40102091431617737, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.09072727710008621, |
|
"min": 0.09072727710008621, |
|
"max": 3.6091883182525635, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 223.03649635036496, |
|
"min": 204.92857142857142, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30556.0, |
|
"min": 16736.0, |
|
"max": 32669.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7632651988794839, |
|
"min": -0.9999871489501768, |
|
"max": 1.794964272316013, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 243.33059744536877, |
|
"min": -30.999601617455482, |
|
"max": 251.29499812424183, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7632651988794839, |
|
"min": -0.9999871489501768, |
|
"max": 1.794964272316013, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 243.33059744536877, |
|
"min": -30.999601617455482, |
|
"max": 251.29499812424183, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.015024319115120992, |
|
"min": 0.014596954533986076, |
|
"max": 7.763516479117029, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.073356037886697, |
|
"min": 1.979329001579572, |
|
"max": 131.9797801449895, |
|
"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": "1679832002", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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=Pyramids1 --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": "1679843793" |
|
}, |
|
"total": 11791.167157627999, |
|
"count": 1, |
|
"self": 0.8452808589991037, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.1298563580003247, |
|
"count": 1, |
|
"self": 0.1298563580003247 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 11790.192020411, |
|
"count": 1, |
|
"self": 7.712836508133478, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.9206680269999197, |
|
"count": 1, |
|
"self": 3.9206680269999197 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 11778.426079532866, |
|
"count": 194747, |
|
"self": 8.118636043982406, |
|
"children": { |
|
"env_step": { |
|
"total": 8183.406791162026, |
|
"count": 194747, |
|
"self": 7741.892572322901, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 437.0267408940085, |
|
"count": 194747, |
|
"self": 22.99007947424161, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 414.0366614197669, |
|
"count": 187570, |
|
"self": 414.0366614197669 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 4.4874779451160975, |
|
"count": 194747, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 11764.174782125228, |
|
"count": 194747, |
|
"is_parallel": true, |
|
"self": 4594.58522178731, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0021881799998482165, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00063519900004394, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015529809998042765, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015529809998042765 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.06623803399997996, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006612440001845243, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000539293999736401, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000539293999736401 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.06313770500037208, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.06313770500037208 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0018997909996869566, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042171999893980683, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014780710007471498, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014780710007471498 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 7169.589560337919, |
|
"count": 194746, |
|
"is_parallel": true, |
|
"self": 136.1175623244908, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 83.57608859527863, |
|
"count": 194746, |
|
"is_parallel": true, |
|
"self": 83.57608859527863 |
|
}, |
|
"communicator.exchange": { |
|
"total": 6551.015613763098, |
|
"count": 194746, |
|
"is_parallel": true, |
|
"self": 6551.015613763098 |
|
}, |
|
"steps_from_proto": { |
|
"total": 398.88029565505076, |
|
"count": 194746, |
|
"is_parallel": true, |
|
"self": 92.14011037233377, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 306.740185282717, |
|
"count": 1557968, |
|
"is_parallel": true, |
|
"self": 306.740185282717 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 3586.900652326859, |
|
"count": 194747, |
|
"self": 15.366107405485764, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 510.95675706935253, |
|
"count": 194747, |
|
"self": 510.14051679435124, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.8162402750012916, |
|
"count": 6, |
|
"self": 0.8162402750012916 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 3060.5777878520207, |
|
"count": 1404, |
|
"self": 1243.9668085360113, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1816.6109793160094, |
|
"count": 68385, |
|
"self": 1816.6109793160094 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2729997251881287e-06, |
|
"count": 1, |
|
"self": 1.2729997251881287e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.13243506999970123, |
|
"count": 1, |
|
"self": 0.003974127999754273, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.12846094199994695, |
|
"count": 1, |
|
"self": 0.12846094199994695 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |