{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.9213847517967224, "min": 0.9213847517967224, "max": 1.4113625288009644, "count": 3 }, "Pyramids.Policy.Entropy.sum": { "value": 27597.31640625, "min": 27597.31640625, "max": 42815.09375, "count": 3 }, "Pyramids.Step.mean": { "value": 89876.0, "min": 29928.0, "max": 89876.0, "count": 3 }, "Pyramids.Step.sum": { "value": 89876.0, "min": 29928.0, "max": 89876.0, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07187079638242722, "min": -0.07187079638242722, "max": 0.03012147732079029, "count": 3 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -17.32086181640625, "min": -17.32086181640625, "max": 7.138790130615234, "count": 3 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.18142572045326233, "min": 0.18142572045326233, "max": 0.500469446182251, "count": 3 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 43.72359848022461, "min": 43.72359848022461, "max": 118.61125183105469, "count": 3 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07094774313788045, "min": 0.07094774313788045, "max": 0.07313650388996827, "count": 3 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8513729176545655, "min": 0.5119555272297779, "max": 0.8513729176545655, "count": 3 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.001153729044529481, "min": 0.001153729044529481, "max": 0.011944368418759944, "count": 3 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.013844748534353772, "min": 0.013844748534353772, "max": 0.08361057893131961, "count": 3 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.665057444983333e-05, "min": 7.665057444983333e-05, "max": 0.0002515063018788571, "count": 3 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009198068933979999, "min": 0.0009198068933979999, "max": 0.0017605441131519997, "count": 3 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.12555016666666668, "min": 0.12555016666666668, "max": 0.1838354285714286, "count": 3 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5066020000000002, "min": 1.2868480000000002, "max": 1.558449, "count": 3 }, "Pyramids.Policy.Beta.mean": { "value": 0.00256246165, "min": 0.00256246165, "max": 0.008385159314285713, "count": 3 }, "Pyramids.Policy.Beta.sum": { "value": 0.0307495398, "min": 0.0307495398, "max": 0.058696115199999996, "count": 3 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.11191242933273315, "min": 0.11191242933273315, "max": 0.5944284200668335, "count": 3 }, "Pyramids.Losses.RNDLoss.sum": { "value": 1.3429491519927979, "min": 1.3429491519927979, "max": 4.160998821258545, "count": 3 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 975.6666666666666, "min": 955.3030303030303, "max": 991.4705882352941, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32197.0, "min": 16855.0, "max": 32197.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.7947091415072932, "min": -0.8747647597509272, "max": -0.7743818698958918, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -26.225401669740677, "min": -26.225401669740677, "max": -14.871000915765762, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.7947091415072932, "min": -0.8747647597509272, "max": -0.7743818698958918, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -26.225401669740677, "min": -26.225401669740677, "max": -14.871000915765762, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 1.2494799105916172, "min": 1.2494799105916172, "max": 12.209093169254416, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 41.23283704952337, "min": 41.23283704952337, "max": 207.55458387732506, "count": 3 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790145118", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda3/envs/mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsFast --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790145344" }, "total": 226.1791096259999, "count": 1, "self": 0.987933116000022, "children": { "run_training.setup": { "total": 0.019194622999975763, "count": 1, "self": 0.019194622999975763 }, "TrainerController.start_learning": { "total": 225.1719818869999, "count": 1, "self": 0.1442979459752678, "children": { "TrainerController._reset_env": { "total": 3.932574829000032, "count": 1, "self": 3.932574829000032 }, "TrainerController.advance": { "total": 220.88404327002468, "count": 6292, "self": 0.14727741700221486, "children": { "env_step": { "total": 154.24278640700618, "count": 6292, "self": 137.63126642001816, "children": { "SubprocessEnvManager._take_step": { "total": 16.52073015398628, "count": 6292, "self": 0.48642044099256054, "children": { "TorchPolicy.evaluate": { "total": 16.034309712993718, "count": 6281, "self": 16.034309712993718 } } }, "workers": { "total": 0.09078983300173604, "count": 6292, "self": 0.0, "children": { "worker_root": { "total": 224.37116895400868, "count": 6292, "is_parallel": true, "self": 99.43518075901034, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0044661069998710445, "count": 1, "is_parallel": true, "self": 0.0031462309996186377, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013198760002524068, "count": 8, "is_parallel": true, "self": 0.0013198760002524068 } } }, "UnityEnvironment.step": { "total": 0.09175766799990015, "count": 1, "is_parallel": true, "self": 0.0005214919999616541, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004857819999415369, "count": 1, "is_parallel": true, "self": 0.0004857819999415369 }, "communicator.exchange": { "total": 0.08691505000001598, "count": 1, "is_parallel": true, "self": 0.08691505000001598 }, "steps_from_proto": { "total": 0.003835343999980978, "count": 1, "is_parallel": true, "self": 0.002379731999781143, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014556120001998352, "count": 8, "is_parallel": true, "self": 0.0014556120001998352 } } } } } } }, "UnityEnvironment.step": { "total": 124.93598819499834, "count": 6291, "is_parallel": true, "self": 3.5497957779900844, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3871883060051005, "count": 6291, "is_parallel": true, "self": 2.3871883060051005 }, "communicator.exchange": { "total": 107.503596986003, "count": 6291, "is_parallel": true, "self": 107.503596986003 }, "steps_from_proto": { "total": 11.495407125000156, "count": 6291, "is_parallel": true, "self": 2.4409444690024884, "children": { "_process_rank_one_or_two_observation": { "total": 9.054462655997668, "count": 50328, "is_parallel": true, "self": 9.054462655997668 } } } } } } } } } } }, "trainer_advance": { "total": 66.49397944601628, "count": 6292, "self": 0.20273106502600058, "children": { "process_trajectory": { "total": 10.906715136990442, "count": 6292, "self": 10.906715136990442 }, "_update_policy": { "total": 55.38453324399984, "count": 34, "self": 30.06015635899871, "children": { "TorchPPOOptimizer.update": { "total": 25.32437688500113, "count": 2322, "self": 25.32437688500113 } } } } } } }, "trainer_threads": { "total": 1.2059999789926223e-06, "count": 1, "self": 1.2059999789926223e-06 }, "TrainerController._save_models": { "total": 0.2110646359999464, "count": 1, "self": 0.0012561449998429453, "children": { "RLTrainer._checkpoint": { "total": 0.20980849100010346, "count": 1, "self": 0.20980849100010346 } } } } } } }