|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2635236084461212, |
|
"min": 0.2635236084461212, |
|
"max": 1.3935461044311523, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 7909.92431640625, |
|
"min": 7909.92431640625, |
|
"max": 42274.61328125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989954.0, |
|
"min": 29878.0, |
|
"max": 989954.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989954.0, |
|
"min": 29878.0, |
|
"max": 989954.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5529126524925232, |
|
"min": -0.09769301116466522, |
|
"max": 0.6089644432067871, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 152.60389709472656, |
|
"min": -23.544015884399414, |
|
"max": 170.51004028320312, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": -0.01647280901670456, |
|
"min": -0.0282344538718462, |
|
"max": 0.490214467048645, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": -4.54649543762207, |
|
"min": -7.849178314208984, |
|
"max": 116.18083190917969, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06941437507852885, |
|
"min": 0.06390797952675105, |
|
"max": 0.0729547766133605, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9718012510994039, |
|
"min": 0.5698626345975972, |
|
"max": 1.0841390616968092, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.017146643080368878, |
|
"min": 0.0007293400353785701, |
|
"max": 0.018541972313112016, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.2400530031251643, |
|
"min": 0.007304103652116075, |
|
"max": 0.27812958469668025, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.297426138985714e-06, |
|
"min": 7.297426138985714e-06, |
|
"max": 0.000294848326717225, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.0001021639659458, |
|
"min": 0.0001021639659458, |
|
"max": 0.003377169174277, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10243244285714286, |
|
"min": 0.10243244285714286, |
|
"max": 0.19828277500000002, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4340542, |
|
"min": 1.4340542, |
|
"max": 2.5724049000000004, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0002530010414285715, |
|
"min": 0.0002530010414285715, |
|
"max": 0.0098284492225, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0035420145800000007, |
|
"min": 0.0035420145800000007, |
|
"max": 0.11258972769999998, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011810539290308952, |
|
"min": 0.011810539290308952, |
|
"max": 0.45249420404434204, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.16534754633903503, |
|
"min": 0.16534754633903503, |
|
"max": 3.6199536323547363, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 335.52272727272725, |
|
"min": 289.15533980582524, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29526.0, |
|
"min": 16421.0, |
|
"max": 34589.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.5025158928368578, |
|
"min": -1.0000000521540642, |
|
"max": 1.673184450245598, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 132.2213985696435, |
|
"min": -32.000001668930054, |
|
"max": 172.3379983752966, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.5025158928368578, |
|
"min": -1.0000000521540642, |
|
"max": 1.673184450245598, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 132.2213985696435, |
|
"min": -32.000001668930054, |
|
"max": 172.3379983752966, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.04132458762019682, |
|
"min": 0.037776939340051066, |
|
"max": 10.200458862325725, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.6365637105773203, |
|
"min": 3.6365637105773203, |
|
"max": 173.40780065953732, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 33 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1684140104", |
|
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --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": "1684142682" |
|
}, |
|
"total": 2577.9646810850004, |
|
"count": 1, |
|
"self": 0.8293707320003705, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.04368076899982043, |
|
"count": 1, |
|
"self": 0.04368076899982043 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2577.091629584, |
|
"count": 1, |
|
"self": 1.707914721958332, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 0.887578029999986, |
|
"count": 1, |
|
"self": 0.887578029999986 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2574.3552631070415, |
|
"count": 63843, |
|
"self": 1.62265351193264, |
|
"children": { |
|
"env_step": { |
|
"total": 1459.8924977459992, |
|
"count": 63843, |
|
"self": 1337.6467430689718, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 121.155560085037, |
|
"count": 63843, |
|
"self": 4.481978640075795, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 116.6735814449612, |
|
"count": 62543, |
|
"self": 116.6735814449612 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.0901945919904392, |
|
"count": 63843, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2572.602448139996, |
|
"count": 63843, |
|
"is_parallel": true, |
|
"self": 1353.757084918961, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0054970899996078515, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0039643479990445485, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.001532742000563303, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.001532742000563303 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.05559759800007669, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005634100002680498, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005149300000084622, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005149300000084622 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.05257968800015078, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.05257968800015078 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0019395699996493931, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00036677999878520495, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0015727900008641882, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0015727900008641882 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1218.8453632210349, |
|
"count": 63842, |
|
"is_parallel": true, |
|
"self": 31.848095973123236, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 17.1880678269531, |
|
"count": 63842, |
|
"is_parallel": true, |
|
"self": 17.1880678269531 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1073.0419694410139, |
|
"count": 63842, |
|
"is_parallel": true, |
|
"self": 1073.0419694410139 |
|
}, |
|
"steps_from_proto": { |
|
"total": 96.76722997994466, |
|
"count": 63842, |
|
"is_parallel": true, |
|
"self": 19.72283001534197, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 77.04439996460269, |
|
"count": 510736, |
|
"is_parallel": true, |
|
"self": 77.04439996460269 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 1112.8401118491097, |
|
"count": 63843, |
|
"self": 3.1853379280692025, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 121.92812987305342, |
|
"count": 63843, |
|
"self": 121.67796498305279, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.250164890000633, |
|
"count": 2, |
|
"self": 0.250164890000633 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 987.7266440479871, |
|
"count": 451, |
|
"self": 290.03570729603416, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 697.6909367519529, |
|
"count": 22758, |
|
"self": 697.6909367519529 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.4500001270789653e-06, |
|
"count": 1, |
|
"self": 1.4500001270789653e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14087227500021982, |
|
"count": 1, |
|
"self": 0.0018256089997521485, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.13904666600046767, |
|
"count": 1, |
|
"self": 0.13904666600046767 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |