|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.11865365505218506, |
|
"min": 0.10541042685508728, |
|
"max": 1.4739055633544922, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 3527.3359375, |
|
"min": 3167.37255859375, |
|
"max": 44712.3984375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999877.0, |
|
"min": 29952.0, |
|
"max": 2999877.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999877.0, |
|
"min": 29952.0, |
|
"max": 2999877.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7665059566497803, |
|
"min": -0.2936858534812927, |
|
"max": 0.8855694532394409, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 231.48480224609375, |
|
"min": -69.60354614257812, |
|
"max": 267.74505615234375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.008230501785874367, |
|
"min": -0.00638219527900219, |
|
"max": 0.4062139093875885, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.4856114387512207, |
|
"min": -1.6338419914245605, |
|
"max": 97.89755249023438, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06905125242476406, |
|
"min": 0.06332516432774035, |
|
"max": 0.07390458639689945, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9667175339466969, |
|
"min": 0.46313406405375, |
|
"max": 1.0899484995655562, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017052337334635445, |
|
"min": 0.00041890551688544353, |
|
"max": 0.017052337334635445, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23873272268489623, |
|
"min": 0.003770149651968992, |
|
"max": 0.24165693658013718, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.4869137901095207e-06, |
|
"min": 1.4869137901095207e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.081679306153329e-05, |
|
"min": 2.081679306153329e-05, |
|
"max": 0.004010769063077, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10049560476190478, |
|
"min": 0.10049560476190478, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4069384666666669, |
|
"min": 1.3962282666666668, |
|
"max": 2.8275326333333326, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 5.951091571428563e-05, |
|
"min": 5.951091571428563e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008331528199999989, |
|
"min": 0.0008331528199999989, |
|
"max": 0.1336986077, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.00911895651370287, |
|
"min": 0.008289322257041931, |
|
"max": 0.435276061296463, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.12766538560390472, |
|
"min": 0.11605051159858704, |
|
"max": 3.0469324588775635, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 220.56204379562044, |
|
"min": 206.25174825174824, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 30217.0, |
|
"min": 15984.0, |
|
"max": 32692.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.765347811460927, |
|
"min": -1.0000000521540642, |
|
"max": 1.7914130324902742, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 243.6179979816079, |
|
"min": -30.72320168465376, |
|
"max": 251.5047977566719, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.765347811460927, |
|
"min": -1.0000000521540642, |
|
"max": 1.7914130324902742, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 243.6179979816079, |
|
"min": -30.72320168465376, |
|
"max": 251.5047977566719, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.020827621046945737, |
|
"min": 0.019732272974846744, |
|
"max": 8.042547635734081, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.874211704478512, |
|
"min": 2.5694642106536776, |
|
"max": 128.6807621717453, |
|
"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": "1677414577", |
|
"python_version": "3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 06:08:53) \n[GCC 9.4.0]", |
|
"command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training_big --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": "1677424419" |
|
}, |
|
"total": 9842.678765529, |
|
"count": 1, |
|
"self": 0.4795583190025354, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.8911535219999678, |
|
"count": 1, |
|
"self": 0.8911535219999678 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 9841.308053687999, |
|
"count": 1, |
|
"self": 7.903677182308456, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 11.629287737999903, |
|
"count": 1, |
|
"self": 11.629287737999903 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 9821.66706515569, |
|
"count": 195510, |
|
"self": 8.540107526465363, |
|
"children": { |
|
"env_step": { |
|
"total": 6535.337809279264, |
|
"count": 195510, |
|
"self": 6105.571293547024, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 425.12835970008825, |
|
"count": 195510, |
|
"self": 22.061832125323235, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 403.066527574765, |
|
"count": 187541, |
|
"self": 85.2255642740588, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 317.8409633007062, |
|
"count": 187541, |
|
"self": 317.8409633007062 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 4.638156032151983, |
|
"count": 195510, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 9827.289793181038, |
|
"count": 195510, |
|
"is_parallel": true, |
|
"self": 4265.744621056255, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.006846225000003869, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004471972999908758, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0023742520000951117, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0023742520000951117 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.053986686000030204, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005002090000516546, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000490298999920924, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000490298999920924 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05140145300003951, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05140145300003951 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015947250000181157, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046503400005803996, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011296909999600757, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011296909999600757 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 5561.545172124784, |
|
"count": 195509, |
|
"is_parallel": true, |
|
"self": 129.13871392320743, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 79.85391634096595, |
|
"count": 195509, |
|
"is_parallel": true, |
|
"self": 79.85391634096595 |
|
}, |
|
"communicator.exchange": { |
|
"total": 5003.162076848672, |
|
"count": 195509, |
|
"is_parallel": true, |
|
"self": 5003.162076848672 |
|
}, |
|
"steps_from_proto": { |
|
"total": 349.390465011938, |
|
"count": 195509, |
|
"is_parallel": true, |
|
"self": 91.99124409877277, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 257.3992209131652, |
|
"count": 1564072, |
|
"is_parallel": true, |
|
"self": 257.3992209131652 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 3277.7891483499616, |
|
"count": 195510, |
|
"self": 15.45308893200854, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 706.9838165629701, |
|
"count": 195510, |
|
"self": 706.2673064459711, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7165101169989612, |
|
"count": 6, |
|
"self": 0.7165101169989612 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 2555.352242854983, |
|
"count": 1398, |
|
"self": 881.4208923539818, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1673.9313505010014, |
|
"count": 68373, |
|
"self": 1673.9313505010014 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.3999997463542968e-06, |
|
"count": 1, |
|
"self": 1.3999997463542968e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10802221199992346, |
|
"count": 1, |
|
"self": 0.002791353001157404, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10523085899876605, |
|
"count": 1, |
|
"self": 0.10523085899876605 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |