|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7905828356742859, |
|
"min": 0.7905828356742859, |
|
"max": 1.4488530158996582, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 23692.185546875, |
|
"min": 23692.185546875, |
|
"max": 43952.40625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479907.0, |
|
"min": 29952.0, |
|
"max": 479907.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479907.0, |
|
"min": 29952.0, |
|
"max": 479907.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.050324004143476486, |
|
"min": -0.14133958518505096, |
|
"max": 0.05295198783278465, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 12.430028915405273, |
|
"min": -33.49748229980469, |
|
"max": 13.026188850402832, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.022865276783704758, |
|
"min": 0.019408101215958595, |
|
"max": 0.3364011347293854, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 5.647723197937012, |
|
"min": 4.774393081665039, |
|
"max": 79.72706604003906, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06561698534601586, |
|
"min": 0.06548031344418126, |
|
"max": 0.0715611568007219, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9186377948442219, |
|
"min": 0.49255309459765373, |
|
"max": 1.0018561952101066, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.0076732196910327816, |
|
"min": 0.001003483737965608, |
|
"max": 0.008528199376384478, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.10742507567445894, |
|
"min": 0.014048772331518513, |
|
"max": 0.10742507567445894, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.1104878679357146e-05, |
|
"min": 2.1104878679357146e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00029546830151100004, |
|
"min": 0.00029546830151100004, |
|
"max": 0.0030854690715104, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10703492857142859, |
|
"min": 0.10703492857142859, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4984890000000002, |
|
"min": 1.3773696000000002, |
|
"max": 2.3386884, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007127893642857145, |
|
"min": 0.0007127893642857145, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.009979051100000002, |
|
"min": 0.009979051100000002, |
|
"max": 0.10287611104000001, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.023121561855077744, |
|
"min": 0.023121561855077744, |
|
"max": 0.45784619450569153, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.3237018585205078, |
|
"min": 0.3237018585205078, |
|
"max": 3.204923391342163, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 817.9444444444445, |
|
"min": 812.0, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29446.0, |
|
"min": 15984.0, |
|
"max": 32958.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 0.2928999567197429, |
|
"min": -1.0000000521540642, |
|
"max": 0.2928999567197429, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 10.544398441910744, |
|
"min": -29.500201620161533, |
|
"max": 10.544398441910744, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 0.2928999567197429, |
|
"min": -1.0000000521540642, |
|
"max": 0.2928999567197429, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 10.544398441910744, |
|
"min": -29.500201620161533, |
|
"max": 10.544398441910744, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.19783258096625408, |
|
"min": 0.19783258096625408, |
|
"max": 9.425822841003537, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 7.121972914785147, |
|
"min": 7.121972914785147, |
|
"max": 150.8131654560566, |
|
"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": "1657271364", |
|
"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": "1657272399" |
|
}, |
|
"total": 1035.552846647, |
|
"count": 1, |
|
"self": 0.4792353269999694, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04348848199998656, |
|
"count": 1, |
|
"self": 0.04348848199998656 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1035.0301228380001, |
|
"count": 1, |
|
"self": 0.7443176909882823, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.186253775000012, |
|
"count": 1, |
|
"self": 10.186253775000012 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1023.9953682310115, |
|
"count": 31601, |
|
"self": 0.7968940850220179, |
|
"children": { |
|
"env_step": { |
|
"total": 654.7717664469998, |
|
"count": 31601, |
|
"self": 598.3025052109763, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 56.07712069400617, |
|
"count": 31601, |
|
"self": 2.4537310670049237, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 53.623389627001245, |
|
"count": 31321, |
|
"self": 18.190058054022188, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 35.43333157297906, |
|
"count": 31321, |
|
"self": 35.43333157297906 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.39214054201733006, |
|
"count": 31601, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1032.863793485993, |
|
"count": 31601, |
|
"is_parallel": true, |
|
"self": 488.29543695196526, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.007559816999958002, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0039324250000163374, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.003627391999941665, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.003627391999941665 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.04908670200001097, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004989720000025955, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.00044811300000446863, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00044811300000446863 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04644686700004286, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04644686700004286 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0016927499999610518, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00041911699992169815, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012736330000393536, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012736330000393536 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 544.5683565340278, |
|
"count": 31600, |
|
"is_parallel": true, |
|
"self": 14.495199145032075, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 12.217369935007241, |
|
"count": 31600, |
|
"is_parallel": true, |
|
"self": 12.217369935007241 |
|
}, |
|
"communicator.exchange": { |
|
"total": 469.1367598579925, |
|
"count": 31600, |
|
"is_parallel": true, |
|
"self": 469.1367598579925 |
|
}, |
|
"steps_from_proto": { |
|
"total": 48.7190275959959, |
|
"count": 31600, |
|
"is_parallel": true, |
|
"self": 12.138001012961183, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 36.58102658303471, |
|
"count": 252800, |
|
"is_parallel": true, |
|
"self": 36.58102658303471 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 368.42670769898973, |
|
"count": 31601, |
|
"self": 1.318300748012689, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 82.1992864399785, |
|
"count": 31601, |
|
"self": 82.0843854469785, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.11490099299999201, |
|
"count": 1, |
|
"self": 0.11490099299999201 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 284.90912051099855, |
|
"count": 219, |
|
"self": 112.24597976199823, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 172.66314074900032, |
|
"count": 11439, |
|
"self": 172.66314074900032 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2500001957960194e-06, |
|
"count": 1, |
|
"self": 1.2500001957960194e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10418189100005293, |
|
"count": 1, |
|
"self": 0.0017239779999727034, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10245791300008023, |
|
"count": 1, |
|
"self": 0.10245791300008023 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |