|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.1264774203300476, |
|
"min": 0.12133873254060745, |
|
"max": 1.469253420829773, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 3784.204345703125, |
|
"min": 3669.283203125, |
|
"max": 44571.2734375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 2999906.0, |
|
"min": 29986.0, |
|
"max": 2999906.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 2999906.0, |
|
"min": 29986.0, |
|
"max": 2999906.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.82927405834198, |
|
"min": -0.07572072744369507, |
|
"max": 0.9394945502281189, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 250.44076538085938, |
|
"min": -18.021533966064453, |
|
"max": 295.00128173828125, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.006171045824885368, |
|
"min": -0.019276633858680725, |
|
"max": 0.22240948677062988, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -1.8636558055877686, |
|
"min": -5.956480026245117, |
|
"max": 52.93345642089844, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.0692730050572815, |
|
"min": 0.06380657659869433, |
|
"max": 0.07588517239185673, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 1.0390950758592226, |
|
"min": 0.5608416392517092, |
|
"max": 1.0846602109183245, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.015756846436609826, |
|
"min": 0.0003106717606486122, |
|
"max": 0.017262691297504466, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.23635269654914737, |
|
"min": 0.003728061127783346, |
|
"max": 0.24167767816506253, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.5075461641844428e-06, |
|
"min": 1.5075461641844428e-06, |
|
"max": 0.00029825500058166664, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 2.2613192462766642e-05, |
|
"min": 2.2613192462766642e-05, |
|
"max": 0.0038843992052002988, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10050248222222224, |
|
"min": 0.10050248222222224, |
|
"max": 0.19941833333333336, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.5075372333333337, |
|
"min": 1.4213532666666668, |
|
"max": 2.752449433333333, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 6.019797399999995e-05, |
|
"min": 6.019797399999995e-05, |
|
"max": 0.009941891500000001, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0009029696099999993, |
|
"min": 0.0009029696099999993, |
|
"max": 0.12949049003000002, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.0068528493866324425, |
|
"min": 0.006573980208486319, |
|
"max": 0.4045696258544922, |
|
"count": 100 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.10279273986816406, |
|
"min": 0.09203572571277618, |
|
"max": 3.2365570068359375, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 216.3985507246377, |
|
"min": 190.873417721519, |
|
"max": 999.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29863.0, |
|
"min": 17424.0, |
|
"max": 32499.0, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.7836014364940533, |
|
"min": -0.9999742459866309, |
|
"max": 1.8086751463117114, |
|
"count": 100 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 246.13699823617935, |
|
"min": -30.999201625585556, |
|
"max": 283.9619979709387, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.7836014364940533, |
|
"min": -0.9999742459866309, |
|
"max": 1.8086751463117114, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 246.13699823617935, |
|
"min": -30.999201625585556, |
|
"max": 283.9619979709387, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.015425271291346491, |
|
"min": 0.013571335901013148, |
|
"max": 8.68073938952552, |
|
"count": 100 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 2.128687438205816, |
|
"min": 1.9685758271371014, |
|
"max": 156.25330901145935, |
|
"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": "1690692381", |
|
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", |
|
"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": "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": "1690700057" |
|
}, |
|
"total": 7676.823282195, |
|
"count": 1, |
|
"self": 0.487801053000112, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.030912136999859285, |
|
"count": 1, |
|
"self": 0.030912136999859285 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 7676.304569004999, |
|
"count": 1, |
|
"self": 4.2867465459448795, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.08383707400003, |
|
"count": 1, |
|
"self": 4.08383707400003 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 7667.823578430056, |
|
"count": 196063, |
|
"self": 4.122779525214355, |
|
"children": { |
|
"env_step": { |
|
"total": 5652.029589080801, |
|
"count": 196063, |
|
"self": 5320.917782719641, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 328.57825031113384, |
|
"count": 196063, |
|
"self": 14.379911542333502, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 314.19833876880034, |
|
"count": 187552, |
|
"self": 314.19833876880034 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.533556050026391, |
|
"count": 196063, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 7658.966845051986, |
|
"count": 196063, |
|
"is_parallel": true, |
|
"self": 2695.4243037460483, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0016969280000012077, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005536460000712395, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011432819999299682, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011432819999299682 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05080075599994416, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005387559999689984, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005018159999963245, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005018159999963245 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.04797005299997181, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.04797005299997181 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017901310000070225, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00034264900000380294, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0014474820000032196, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0014474820000032196 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 4963.542541305937, |
|
"count": 196062, |
|
"is_parallel": true, |
|
"self": 103.71747368603246, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 68.94208805377593, |
|
"count": 196062, |
|
"is_parallel": true, |
|
"self": 68.94208805377593 |
|
}, |
|
"communicator.exchange": { |
|
"total": 4481.419380136015, |
|
"count": 196062, |
|
"is_parallel": true, |
|
"self": 4481.419380136015 |
|
}, |
|
"steps_from_proto": { |
|
"total": 309.4635994301145, |
|
"count": 196062, |
|
"is_parallel": true, |
|
"self": 62.81913088212218, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 246.64446854799235, |
|
"count": 1568496, |
|
"is_parallel": true, |
|
"self": 246.64446854799235 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2011.6712098240403, |
|
"count": 196063, |
|
"self": 8.25805797199314, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 347.73920588205806, |
|
"count": 196063, |
|
"self": 347.07214390705917, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.6670619749988873, |
|
"count": 6, |
|
"self": 0.6670619749988873 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1655.673945969989, |
|
"count": 1399, |
|
"self": 1077.678762597906, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 577.9951833720831, |
|
"count": 68358, |
|
"self": 577.9951833720831 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.78999344422482e-07, |
|
"count": 1, |
|
"self": 8.78999344422482e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.11040607599898067, |
|
"count": 1, |
|
"self": 0.0014532119985233294, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.10895286400045734, |
|
"count": 1, |
|
"self": 0.10895286400045734 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |