|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.18839456140995026, |
|
"min": 0.1832941323518753, |
|
"max": 1.436747431755066, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 5663.89404296875, |
|
"min": 5475.22900390625, |
|
"max": 43585.171875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999968.0, |
|
"min": 29952.0, |
|
"max": 2999968.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999968.0, |
|
"min": 29952.0, |
|
"max": 2999968.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.7405109405517578, |
|
"min": -0.10107098519802094, |
|
"max": 0.8416146039962769, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 216.22918701171875, |
|
"min": -24.35810661315918, |
|
"max": 251.64276123046875, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.023741815239191055, |
|
"min": -0.01568537764251232, |
|
"max": 0.38278132677078247, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 6.932610034942627, |
|
"min": -4.438961982727051, |
|
"max": 92.25029754638672, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07276394912748531, |
|
"min": 0.06402329153241314, |
|
"max": 0.07321170100823067, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0186952877847943, |
|
"min": 0.4969161504084424, |
|
"max": 1.0923398902220882, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.01480409925750878, |
|
"min": 0.0006634425429559791, |
|
"max": 0.018006423953227654, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2072573896051229, |
|
"min": 0.008624753058427729, |
|
"max": 0.25208993534518714, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5321994892999986e-06, |
|
"min": 1.5321994892999986e-06, |
|
"max": 0.00029838354339596195, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.145079285019998e-05, |
|
"min": 2.145079285019998e-05, |
|
"max": 0.0040109539630153665, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10051070000000002, |
|
"min": 0.10051070000000002, |
|
"max": 0.19946118095238097, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4071498000000002, |
|
"min": 1.3962282666666668, |
|
"max": 2.736984633333334, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.101892999999996e-05, |
|
"min": 6.101892999999996e-05, |
|
"max": 0.009946171977142856, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0008542650199999995, |
|
"min": 0.0008542650199999995, |
|
"max": 0.13370476487, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.007593870162963867, |
|
"min": 0.0072589293122291565, |
|
"max": 0.5914143919944763, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10631418228149414, |
|
"min": 0.10162501037120819, |
|
"max": 4.1399006843566895, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 248.78813559322035, |
|
"min": 218.7537313432836, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29357.0, |
|
"min": 15984.0, |
|
"max": 33293.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7342542247625732, |
|
"min": -1.0000000521540642, |
|
"max": 1.7787132188677788, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 204.64199852198362, |
|
"min": -29.956001602113247, |
|
"max": 241.9049977660179, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7342542247625732, |
|
"min": -1.0000000521540642, |
|
"max": 1.7787132188677788, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 204.64199852198362, |
|
"min": -29.956001602113247, |
|
"max": 241.9049977660179, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.0195393039597301, |
|
"min": 0.016915114604522222, |
|
"max": 12.05250214971602, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.3056378672481515, |
|
"min": 2.1160940441623097, |
|
"max": 192.8400343954563, |
|
"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": "1722303710", |
|
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", |
|
"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": "1.1.0.dev0", |
|
"mlagents_envs_version": "1.1.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "2.3.1+cu121", |
|
"numpy_version": "1.23.5", |
|
"end_time_seconds": "1722315833" |
|
}, |
|
"total": 12123.303412471001, |
|
"count": 1, |
|
"self": 0.6947380680012429, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11338866100004452, |
|
"count": 1, |
|
"self": 0.11338866100004452 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 12122.495285742, |
|
"count": 1, |
|
"self": 8.560820317234175, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.139138100000082, |
|
"count": 1, |
|
"self": 3.139138100000082 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 12110.685955304765, |
|
"count": 194328, |
|
"self": 10.048373114923379, |
|
"children": { |
|
"env_step": { |
|
"total": 8469.42242347385, |
|
"count": 194328, |
|
"self": 7881.9022959216145, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 582.2071206779208, |
|
"count": 194328, |
|
"self": 27.025408596966372, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 555.1817120809544, |
|
"count": 187562, |
|
"self": 555.1817120809544 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 5.313006874314624, |
|
"count": 194328, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 12094.24655994405, |
|
"count": 194328, |
|
"is_parallel": true, |
|
"self": 4909.1635515697635, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0035330829998656554, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0011351679997915198, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0023979150000741356, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0023979150000741356 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.08049550999999155, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008801609999409266, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005924130000494188, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005924130000494188 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.07690504199990755, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.07690504199990755 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0021178940000936564, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00046309599974847515, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0016547980003451812, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0016547980003451812 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 7185.083008374286, |
|
"count": 194327, |
|
"is_parallel": true, |
|
"self": 180.00613906615217, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 102.99308308713194, |
|
"count": 194327, |
|
"is_parallel": true, |
|
"self": 102.99308308713194 |
|
}, |
|
"communicator.exchange": { |
|
"total": 6471.387142303279, |
|
"count": 194327, |
|
"is_parallel": true, |
|
"self": 6471.387142303279 |
|
}, |
|
"steps_from_proto": { |
|
"total": 430.6966439177229, |
|
"count": 194327, |
|
"is_parallel": true, |
|
"self": 97.75706567459792, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 332.93957824312497, |
|
"count": 1554616, |
|
"is_parallel": true, |
|
"self": 332.93957824312497 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 3631.2151587159915, |
|
"count": 194328, |
|
"self": 19.1745339693598, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 590.5785973666418, |
|
"count": 194328, |
|
"self": 589.9334512216421, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6451461449996714, |
|
"count": 6, |
|
"self": 0.6451461449996714 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 3021.4620273799896, |
|
"count": 1398, |
|
"self": 1208.3197295310329, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 1813.1422978489568, |
|
"count": 68409, |
|
"self": 1813.1422978489568 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.0809999366756529e-06, |
|
"count": 1, |
|
"self": 1.0809999366756529e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.1093709390006552, |
|
"count": 1, |
|
"self": 0.0027942490014538635, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10657668999920134, |
|
"count": 1, |
|
"self": 0.10657668999920134 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |