{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.19593621790409088, "min": 0.18135128915309906, "max": 1.4679837226867676, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 5925.111328125, "min": 5452.14501953125, "max": 44532.75390625, "count": 66 }, "Pyramids.Step.mean": { "value": 1979961.0, "min": 29952.0, "max": 1979961.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979961.0, "min": 29952.0, "max": 1979961.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7173455953598022, "min": -0.08874265104532242, "max": 0.8296836018562317, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 212.33428955078125, "min": -21.298236846923828, "max": 253.8831787109375, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0003342825220897794, "min": -0.007599753327667713, "max": 0.6566954255104065, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.09894762933254242, "min": -2.2951254844665527, "max": 155.63681030273438, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06857218653432723, "min": 0.06413555388490923, "max": 0.07490956852589513, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0285827980149085, "min": 0.52379409238949, "max": 1.0690076710501066, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014588604698541995, "min": 0.0004832045657261958, "max": 0.01590774849492369, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2188290704781299, "min": 0.005315250222988154, "max": 0.2373526686084612, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.976221575650002e-06, "min": 5.976221575650002e-06, "max": 0.0003372520236653715, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.964332363475003e-05, "min": 8.964332363475003e-05, "max": 0.004223965167657351, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10175768333333331, "min": 0.10175768333333331, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5263652499999996, "min": 1.3943424, "max": 2.6513022000000004, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018559256500000004, "min": 0.00018559256500000004, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.0027838884750000007, "min": 0.0027838884750000007, "max": 0.12425003073500002, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006712593138217926, "min": 0.006492404732853174, "max": 0.49319568276405334, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10068889707326889, "min": 0.09089366346597672, "max": 3.4523696899414062, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 273.69565217391306, "min": 217.8235294117647, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31475.0, "min": 15984.0, "max": 33260.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6741112854169762, "min": -1.0000000521540642, "max": 1.7733511343484616, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.52279782295227, "min": -31.999601677060127, "max": 240.2503986954689, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6741112854169762, "min": -1.0000000521540642, "max": 1.7733511343484616, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.52279782295227, "min": -31.999601677060127, "max": 240.2503986954689, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019038819999727622, "min": 0.015872363847137402, "max": 10.959095973521471, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1894642999686766, "min": 1.9536741457995959, "max": 175.34553557634354, "count": 66 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702911633", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702916629" }, "total": 4995.967483816999, "count": 1, "self": 0.47641097900032037, "children": { "run_training.setup": { "total": 0.04988553899966064, "count": 1, "self": 0.04988553899966064 }, "TrainerController.start_learning": { "total": 4995.4411872989995, "count": 1, "self": 3.1810825380653114, "children": { "TrainerController._reset_env": { "total": 2.224548134000088, "count": 1, "self": 2.224548134000088 }, "TrainerController.advance": { "total": 4989.943705978933, "count": 129359, "self": 3.2286951829491954, "children": { "env_step": { "total": 3693.9778236580114, "count": 129359, "self": 3413.0291321272466, "children": { "SubprocessEnvManager._take_step": { "total": 278.9382107049337, "count": 129359, "self": 10.260352484872328, "children": { "TorchPolicy.evaluate": { "total": 268.67785822006135, "count": 125060, "self": 268.67785822006135 } } }, "workers": { "total": 2.0104808258311095, "count": 129359, "self": 0.0, "children": { "worker_root": { "total": 4983.87277686697, "count": 129359, "is_parallel": true, "self": 1836.7107776388257, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018087190001097042, "count": 1, "is_parallel": true, "self": 0.0006253760002437048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011833429998659994, "count": 8, "is_parallel": true, "self": 0.0011833429998659994 } } }, "UnityEnvironment.step": { "total": 0.07885554700033026, "count": 1, "is_parallel": true, "self": 0.0005980920004731161, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044997999975748826, "count": 1, "is_parallel": true, "self": 0.00044997999975748826 }, "communicator.exchange": { "total": 0.07611652500008859, "count": 1, "is_parallel": true, "self": 0.07611652500008859 }, "steps_from_proto": { "total": 0.001690950000011071, "count": 1, "is_parallel": true, "self": 0.0003435629996602074, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013473870003508637, "count": 8, "is_parallel": true, "self": 0.0013473870003508637 } } } } } } }, "UnityEnvironment.step": { "total": 3147.161999228144, "count": 129358, "is_parallel": true, "self": 73.09813539426932, "children": { "UnityEnvironment._generate_step_input": { "total": 52.83679982310514, "count": 129358, "is_parallel": true, "self": 52.83679982310514 }, "communicator.exchange": { "total": 2806.8263952748243, "count": 129358, "is_parallel": true, "self": 2806.8263952748243 }, "steps_from_proto": { "total": 214.40066873594515, "count": 129358, "is_parallel": true, "self": 44.4393719286586, "children": { "_process_rank_one_or_two_observation": { "total": 169.96129680728654, "count": 1034864, "is_parallel": true, "self": 169.96129680728654 } } } } } } } } } } }, "trainer_advance": { "total": 1292.7371871379733, "count": 129359, "self": 6.1875671259526825, "children": { "process_trajectory": { "total": 274.1138405380243, "count": 129359, "self": 273.5613292140242, "children": { "RLTrainer._checkpoint": { "total": 0.5525113240000792, "count": 4, "self": 0.5525113240000792 } } }, "_update_policy": { "total": 1012.4357794739963, "count": 919, "self": 602.3328376130085, "children": { "TorchPPOOptimizer.update": { "total": 410.1029418609878, "count": 45600, "self": 410.1029418609878 } } } } } } }, "trainer_threads": { "total": 1.1299998732283711e-06, "count": 1, "self": 1.1299998732283711e-06 }, "TrainerController._save_models": { "total": 0.09184951800034469, "count": 1, "self": 0.0015475990003324114, "children": { "RLTrainer._checkpoint": { "total": 0.09030191900001228, "count": 1, "self": 0.09030191900001228 } } } } } } }