aliakyurek's picture
first attempt
0ac3d0d
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6912637948989868,
"min": 0.6912637948989868,
"max": 1.430425763130188,
"count": 19
},
"Pyramids.Policy.Entropy.sum": {
"value": 20903.81640625,
"min": 20903.81640625,
"max": 43393.39453125,
"count": 19
},
"Pyramids.Step.mean": {
"value": 569992.0,
"min": 29952.0,
"max": 569992.0,
"count": 19
},
"Pyramids.Step.sum": {
"value": 569992.0,
"min": 29952.0,
"max": 569992.0,
"count": 19
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3280133903026581,
"min": -0.08372107893228531,
"max": 0.4330156147480011,
"count": 19
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 84.62745666503906,
"min": -20.176780700683594,
"max": 114.74913787841797,
"count": 19
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.030363300815224648,
"min": 0.003907750826328993,
"max": 0.4433678090572357,
"count": 19
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.833731651306152,
"min": 1.0394617319107056,
"max": 105.07817077636719,
"count": 19
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06693510291506881,
"min": 0.06474084275610306,
"max": 0.07348663274093443,
"count": 19
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9370914408109634,
"min": 0.49843009129626914,
"max": 1.0397216044172335,
"count": 19
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011320327436615037,
"min": 0.0011785823907635277,
"max": 0.017260542356160438,
"count": 19
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.15848458411261052,
"min": 0.014142988689162334,
"max": 0.21254795896432674,
"count": 19
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00013350479121270714,
"min": 0.00013350479121270714,
"max": 0.00029515063018788575,
"count": 19
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0018690670769779,
"min": 0.0018690670769779,
"max": 0.0035073719308760997,
"count": 19
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1445015785714286,
"min": 0.1445015785714286,
"max": 0.19838354285714285,
"count": 19
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.0230221000000004,
"min": 1.3886848,
"max": 2.5726254000000006,
"count": 19
},
"Pyramids.Policy.Beta.mean": {
"value": 0.004455707699285714,
"min": 0.004455707699285714,
"max": 0.00983851593142857,
"count": 19
},
"Pyramids.Policy.Beta.sum": {
"value": 0.06237990779,
"min": 0.06237990779,
"max": 0.11693547761,
"count": 19
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.015322028659284115,
"min": 0.015322028659284115,
"max": 0.5654403567314148,
"count": 19
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.21450839936733246,
"min": 0.21450839936733246,
"max": 3.958082437515259,
"count": 19
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 551.3090909090909,
"min": 430.74285714285713,
"max": 999.0,
"count": 19
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30322.0,
"min": 15984.0,
"max": 33567.0,
"count": 19
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1257708824493668,
"min": -1.0000000521540642,
"max": 1.406430280795603,
"count": 19
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 61.917398534715176,
"min": -29.830601632595062,
"max": 98.42099809646606,
"count": 19
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1257708824493668,
"min": -1.0000000521540642,
"max": 1.406430280795603,
"count": 19
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 61.917398534715176,
"min": -29.830601632595062,
"max": 98.42099809646606,
"count": 19
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.08862656999315897,
"min": 0.07311969641762386,
"max": 12.168980139307678,
"count": 19
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.8744613496237434,
"min": 4.8744613496237434,
"max": 194.70368222892284,
"count": 19
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684843193",
"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=Pyramids Training1 --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": "1684844855"
},
"total": 1661.751447867,
"count": 1,
"self": 0.6468350869999995,
"children": {
"run_training.setup": {
"total": 0.06572927500019432,
"count": 1,
"self": 0.06572927500019432
},
"TrainerController.start_learning": {
"total": 1661.0388835049998,
"count": 1,
"self": 1.2353984080118607,
"children": {
"TrainerController._reset_env": {
"total": 5.753493822999644,
"count": 1,
"self": 5.753493822999644
},
"TrainerController.advance": {
"total": 1654.0439975579889,
"count": 36411,
"self": 1.2521198529757385,
"children": {
"env_step": {
"total": 1188.0520964869388,
"count": 36411,
"self": 1094.521070230966,
"children": {
"SubprocessEnvManager._take_step": {
"total": 92.80486601196117,
"count": 36411,
"self": 4.104510902051516,
"children": {
"TorchPolicy.evaluate": {
"total": 88.70035510990965,
"count": 35876,
"self": 88.70035510990965
}
}
},
"workers": {
"total": 0.7261602440116803,
"count": 36410,
"self": 0.0,
"children": {
"worker_root": {
"total": 1656.580796955022,
"count": 36410,
"is_parallel": true,
"self": 657.8794417150066,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004319632999795431,
"count": 1,
"is_parallel": true,
"self": 0.001927778000208491,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00239185499958694,
"count": 8,
"is_parallel": true,
"self": 0.00239185499958694
}
}
},
"UnityEnvironment.step": {
"total": 0.06228353000005882,
"count": 1,
"is_parallel": true,
"self": 0.0006419029996322934,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005533789999390137,
"count": 1,
"is_parallel": true,
"self": 0.0005533789999390137
},
"communicator.exchange": {
"total": 0.0589434850003272,
"count": 1,
"is_parallel": true,
"self": 0.0589434850003272
},
"steps_from_proto": {
"total": 0.00214476300016031,
"count": 1,
"is_parallel": true,
"self": 0.0004533360006462317,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016914269995140785,
"count": 8,
"is_parallel": true,
"self": 0.0016914269995140785
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 998.7013552400153,
"count": 36409,
"is_parallel": true,
"self": 25.22823409698958,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 17.575657420004973,
"count": 36409,
"is_parallel": true,
"self": 17.575657420004973
},
"communicator.exchange": {
"total": 881.4655145989941,
"count": 36409,
"is_parallel": true,
"self": 881.4655145989941
},
"steps_from_proto": {
"total": 74.43194912402669,
"count": 36409,
"is_parallel": true,
"self": 16.183538886766655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.24841023726003,
"count": 291272,
"is_parallel": true,
"self": 58.24841023726003
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.7397812180743,
"count": 36410,
"self": 2.30698482108437,
"children": {
"process_trajectory": {
"total": 76.35077619098683,
"count": 36410,
"self": 76.22134242598713,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12943376499970327,
"count": 1,
"self": 0.12943376499970327
}
}
},
"_update_policy": {
"total": 386.0820202060031,
"count": 255,
"self": 243.52883064899925,
"children": {
"TorchPPOOptimizer.update": {
"total": 142.55318955700386,
"count": 13098,
"self": 142.55318955700386
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6209996829275042e-06,
"count": 1,
"self": 1.6209996829275042e-06
},
"TrainerController._save_models": {
"total": 0.0059920949997831485,
"count": 1,
"self": 5.2149000111967325e-05,
"children": {
"RLTrainer._checkpoint": {
"total": 0.005939945999671181,
"count": 1,
"self": 0.005939945999671181
}
}
}
}
}
}
}