|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.7376081943511963, |
|
"min": 0.7376081943511963, |
|
"max": 1.4347764253616333, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 22092.83984375, |
|
"min": 22092.83984375, |
|
"max": 43525.37890625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 479905.0, |
|
"min": 29952.0, |
|
"max": 479905.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 479905.0, |
|
"min": 29952.0, |
|
"max": 479905.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.022917557507753372, |
|
"min": -0.12516728043556213, |
|
"max": 0.14653901755809784, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -5.591884136199951, |
|
"min": -30.04014778137207, |
|
"max": 34.7297477722168, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.011977709829807281, |
|
"min": 0.00611144071444869, |
|
"max": 0.24402427673339844, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 2.9225611686706543, |
|
"min": 1.478968620300293, |
|
"max": 58.565826416015625, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07165605075548, |
|
"min": 0.06319745854259871, |
|
"max": 0.0729989165579078, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.00318471057672, |
|
"min": 0.48017553809090874, |
|
"max": 1.0150389934676443, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.003922808469266681, |
|
"min": 0.00017044378441988213, |
|
"max": 0.0059971272449223165, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.05491931856973353, |
|
"min": 0.001193106490939175, |
|
"max": 0.07535271729177431, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 2.156786423931428e-05, |
|
"min": 2.156786423931428e-05, |
|
"max": 0.00029030126037577137, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0003019500993503999, |
|
"min": 0.0003019500993503999, |
|
"max": 0.0021562625812460005, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10718925714285714, |
|
"min": 0.10718925714285714, |
|
"max": 0.19676708571428575, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5006496, |
|
"min": 1.1701888, |
|
"max": 2.018754, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0007282067885714287, |
|
"min": 0.0007282067885714287, |
|
"max": 0.00967703186285714, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.01019489504, |
|
"min": 0.01019489504, |
|
"max": 0.07193352459999999, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.020340751856565475, |
|
"min": 0.020340751856565475, |
|
"max": 0.35770383477211, |
|
"count": 16 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.28477051854133606, |
|
"min": 0.28477051854133606, |
|
"max": 2.5039267539978027, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 912.6176470588235, |
|
"min": 865.3055555555555, |
|
"max": 999.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 31029.0, |
|
"min": 15984.0, |
|
"max": 31968.0, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": -0.3836706357405466, |
|
"min": -1.0000000521540642, |
|
"max": -0.19908892839319176, |
|
"count": 16 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": -13.044801615178585, |
|
"min": -32.000001668930054, |
|
"max": -7.167201422154903, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": -0.3836706357405466, |
|
"min": -1.0000000521540642, |
|
"max": -0.19908892839319176, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": -13.044801615178585, |
|
"min": -32.000001668930054, |
|
"max": -7.167201422154903, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.19226156707223066, |
|
"min": 0.19226156707223066, |
|
"max": 6.720401773229241, |
|
"count": 16 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 6.536893280455843, |
|
"min": 6.536893280455843, |
|
"max": 107.52642837166786, |
|
"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": "1660942166", |
|
"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": "1660943098" |
|
}, |
|
"total": 932.405891352, |
|
"count": 1, |
|
"self": 0.47755846099994415, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04169316499996967, |
|
"count": 1, |
|
"self": 0.04169316499996967 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 931.8866397260001, |
|
"count": 1, |
|
"self": 0.6573253499847169, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.363247745999956, |
|
"count": 1, |
|
"self": 10.363247745999956 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 920.7708057630155, |
|
"count": 31505, |
|
"self": 0.6989882300242698, |
|
"children": { |
|
"env_step": { |
|
"total": 562.9681373970069, |
|
"count": 31505, |
|
"self": 510.5003465470128, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 52.11612102399499, |
|
"count": 31505, |
|
"self": 2.2772967379970623, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 49.83882428599793, |
|
"count": 31324, |
|
"self": 16.967424204008353, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 32.87140008198958, |
|
"count": 31324, |
|
"self": 32.87140008198958 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.35166982599912444, |
|
"count": 31505, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 929.8279945290066, |
|
"count": 31505, |
|
"is_parallel": true, |
|
"self": 469.2585843840086, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00523813400002382, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.004049410999982683, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011887230000411364, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011887230000411364 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.047461717999908615, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004995249998955842, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000454087999969488, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000454087999969488 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04491655900005753, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04491655900005753 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0015915459999860104, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0004124369997953181, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011791090001906923, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011791090001906923 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 460.56941014499796, |
|
"count": 31504, |
|
"is_parallel": true, |
|
"self": 13.453589531009015, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 11.295920657001034, |
|
"count": 31504, |
|
"is_parallel": true, |
|
"self": 11.295920657001034 |
|
}, |
|
"communicator.exchange": { |
|
"total": 390.6960824149977, |
|
"count": 31504, |
|
"is_parallel": true, |
|
"self": 390.6960824149977 |
|
}, |
|
"steps_from_proto": { |
|
"total": 45.123817541990206, |
|
"count": 31504, |
|
"is_parallel": true, |
|
"self": 11.082685498004594, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 34.04113204398561, |
|
"count": 252032, |
|
"is_parallel": true, |
|
"self": 34.04113204398561 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 357.1036801359843, |
|
"count": 31505, |
|
"self": 1.0444641319820676, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 78.15251227400177, |
|
"count": 31505, |
|
"self": 78.0441957830019, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10831649099986862, |
|
"count": 1, |
|
"self": 0.10831649099986862 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 277.90670373000046, |
|
"count": 186, |
|
"self": 112.0213123279982, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 165.88539140200226, |
|
"count": 11496, |
|
"self": 165.88539140200226 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0080000265588751e-06, |
|
"count": 1, |
|
"self": 1.0080000265588751e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.09525985899995248, |
|
"count": 1, |
|
"self": 0.0016372319998936291, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.09362262700005886, |
|
"count": 1, |
|
"self": 0.09362262700005886 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |