{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3757832646369934, "min": 0.3757832646369934, "max": 1.5035514831542969, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11237.4228515625, "min": 11237.4228515625, "max": 45611.73828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989900.0, "min": 29952.0, "max": 989900.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.389853298664093, "min": -0.1707008183002472, "max": 0.4719642996788025, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 103.70097351074219, "min": -40.456092834472656, "max": 126.01446533203125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0784243568778038, "min": -0.0784243568778038, "max": 0.4287486672401428, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.86087989807129, "min": -20.86087989807129, "max": 101.61343383789062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.065272511795756, "min": 0.06517847132457401, "max": 0.07344215022673858, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9138151651405839, "min": 0.4732278723437968, "max": 1.074487338262021, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01375165175698637, "min": 0.0002537432488184953, "max": 0.015556081277202944, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19252312459780918, "min": 0.0035524054834589337, "max": 0.21778513788084122, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.649626021585711e-06, "min": 7.649626021585711e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010709476430219997, "min": 0.00010709476430219997, "max": 0.003507482630839199, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254984285714287, "min": 0.10254984285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356978000000002, "min": 1.3691136000000002, "max": 2.5691608, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002647293014285714, "min": 0.0002647293014285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037062102199999993, "min": 0.0037062102199999993, "max": 0.11693916392, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009514533914625645, "min": 0.009429880417883396, "max": 0.3804333209991455, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13320347666740417, "min": 0.1320183277130127, "max": 2.6630332469940186, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 454.04285714285714, "min": 379.67123287671234, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31783.0, "min": 15984.0, "max": 33272.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2887428284755775, "min": -1.0000000521540642, "max": 1.538115046203953, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.21199799329042, "min": -32.000001668930054, "max": 112.28239837288857, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2887428284755775, "min": -1.0000000521540642, "max": 1.538115046203953, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.21199799329042, "min": -32.000001668930054, "max": 112.28239837288857, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044591708348265716, "min": 0.03986862669172633, "max": 7.703050270676613, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1214195843786, "min": 2.910409748496022, "max": 123.2488043308258, "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": "1685626753", "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 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": "1685630579" }, "total": 3826.230357075, "count": 1, "self": 0.679875906000234, "children": { "run_training.setup": { "total": 0.09563706199969602, "count": 1, "self": 0.09563706199969602 }, "TrainerController.start_learning": { "total": 3825.454844107, "count": 1, "self": 2.7342276421713905, "children": { "TrainerController._reset_env": { "total": 1.6826567909993173, "count": 1, "self": 1.6826567909993173 }, "TrainerController.advance": { "total": 3820.9184493808298, "count": 63535, "self": 2.9993685789095252, "children": { "env_step": { "total": 2501.3572682350023, "count": 63535, "self": 2337.653972473934, "children": { "SubprocessEnvManager._take_step": { "total": 162.01183583197871, "count": 63535, "self": 8.06498643402847, "children": { "TorchPolicy.evaluate": { "total": 153.94684939795025, "count": 62560, "self": 153.94684939795025 } } }, "workers": { "total": 1.691459929089433, "count": 63535, "self": 0.0, "children": { "worker_root": { "total": 3817.2191223609416, "count": 63535, "is_parallel": true, "self": 1677.966873298893, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004436889999851701, "count": 1, "is_parallel": true, "self": 0.0013685410003745346, "children": { "_process_rank_one_or_two_observation": { "total": 0.003068348999477166, "count": 8, "is_parallel": true, "self": 0.003068348999477166 } } }, "UnityEnvironment.step": { "total": 0.1898665250000704, "count": 1, "is_parallel": true, "self": 0.0007955279997986509, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000684134999573871, "count": 1, "is_parallel": true, "self": 0.000684134999573871 }, "communicator.exchange": { "total": 0.1855386080005701, "count": 1, "is_parallel": true, "self": 0.1855386080005701 }, "steps_from_proto": { "total": 0.002848254000127781, "count": 1, "is_parallel": true, "self": 0.0006010879997120355, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022471660004157457, "count": 8, "is_parallel": true, "self": 0.0022471660004157457 } } } } } } }, "UnityEnvironment.step": { "total": 2139.2522490620486, "count": 63534, "is_parallel": true, "self": 49.98774896411214, "children": { "UnityEnvironment._generate_step_input": { "total": 28.657489012979568, "count": 63534, "is_parallel": true, "self": 28.657489012979568 }, "communicator.exchange": { "total": 1912.3794053690253, "count": 63534, "is_parallel": true, "self": 1912.3794053690253 }, "steps_from_proto": { "total": 148.22760571593153, "count": 63534, "is_parallel": true, "self": 32.01261343258648, "children": { "_process_rank_one_or_two_observation": { "total": 116.21499228334505, "count": 508272, "is_parallel": true, "self": 116.21499228334505 } } } } } } } } } } }, "trainer_advance": { "total": 1316.561812566918, "count": 63535, "self": 5.409694219982157, "children": { "process_trajectory": { "total": 167.66807079192586, "count": 63535, "self": 167.31078755492672, "children": { "RLTrainer._checkpoint": { "total": 0.35728323699913744, "count": 2, "self": 0.35728323699913744 } } }, "_update_policy": { "total": 1143.48404755501, "count": 443, "self": 455.30898121391965, "children": { "TorchPPOOptimizer.update": { "total": 688.1750663410903, "count": 22791, "self": 688.1750663410903 } } } } } } }, "trainer_threads": { "total": 1.225999767484609e-06, "count": 1, "self": 1.225999767484609e-06 }, "TrainerController._save_models": { "total": 0.11950906699985353, "count": 1, "self": 0.0019971199999417877, "children": { "RLTrainer._checkpoint": { "total": 0.11751194699991174, "count": 1, "self": 0.11751194699991174 } } } } } } }