{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.628937304019928, "min": 0.628937304019928, "max": 1.4676501750946045, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 18817.8046875, "min": 18817.8046875, "max": 44522.63671875, "count": 16 }, "Pyramids.Step.mean": { "value": 479965.0, "min": 29952.0, "max": 479965.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479965.0, "min": 29952.0, "max": 479965.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.059049010276794434, "min": -0.11635548621416092, "max": 0.059049010276794434, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 14.585105895996094, "min": -27.925315856933594, "max": 14.585105895996094, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03014584630727768, "min": 0.022145874798297882, "max": 0.2874983549118042, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.446023941040039, "min": 5.425739288330078, "max": 68.99960327148438, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06470945735539621, "min": 0.06470945735539621, "max": 0.07591437357534714, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9059324029755469, "min": 0.48682498098310917, "max": 1.0035876971121658, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007463052369790342, "min": 0.0006259439133766162, "max": 0.007463052369790342, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10448273317706479, "min": 0.005633495220389546, "max": 0.10448273317706479, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.07711930763e-05, "min": 2.07711930763e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029079670306819997, "min": 0.00029079670306819997, "max": 0.002849349250217, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1069237, "min": 0.1069237, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4969318, "min": 1.3382272, "max": 2.3383858, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007016776300000002, "min": 0.0007016776300000002, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009823486820000003, "min": 0.009823486820000003, "max": 0.09500332170000002, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02501296065747738, "min": 0.02501296065747738, "max": 0.4166910648345947, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3501814603805542, "min": 0.3501814603805542, "max": 2.916837453842163, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 735.1052631578947, "min": 735.1052631578947, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27934.0, "min": 15984.0, "max": 33840.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.2974864522347579, "min": -1.0000000521540642, "max": 0.2974864522347579, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 11.006998732686043, "min": -32.000001668930054, "max": 11.006998732686043, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.2974864522347579, "min": -1.0000000521540642, "max": 0.2974864522347579, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 11.006998732686043, "min": -32.000001668930054, "max": 11.006998732686043, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.19294533719359017, "min": 0.19294533719359017, "max": 7.766000689007342, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 7.138977476162836, "min": 7.138977476162836, "max": 124.25601102411747, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1784128627", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1784129786" }, "total": 1159.0254272999998, "count": 1, "self": 0.4837844490000407, "children": { "run_training.setup": { "total": 0.024408304999951724, "count": 1, "self": 0.024408304999951724 }, "TrainerController.start_learning": { "total": 1158.5172345459998, "count": 1, "self": 0.7400688780294331, "children": { "TrainerController._reset_env": { "total": 2.246704305999856, "count": 1, "self": 2.246704305999856 }, "TrainerController.advance": { "total": 1155.4343687699707, "count": 31613, "self": 0.7314303729533549, "children": { "env_step": { "total": 824.1302995820452, "count": 31613, "self": 742.8434857280565, "children": { "SubprocessEnvManager._take_step": { "total": 80.86104406599884, "count": 31613, "self": 2.5253346260260514, "children": { "TorchPolicy.evaluate": { "total": 78.33570943997279, "count": 31302, "self": 78.33570943997279 } } }, "workers": { "total": 0.42576978798979326, "count": 31613, "self": 0.0, "children": { "worker_root": { "total": 1155.619174575035, "count": 31613, "is_parallel": true, "self": 475.44240084506123, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001909277999857295, "count": 1, "is_parallel": true, "self": 0.0006505189999188588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012587589999384363, "count": 8, "is_parallel": true, "self": 0.0012587589999384363 } } }, "UnityEnvironment.step": { "total": 0.056508910999809814, "count": 1, "is_parallel": true, "self": 0.0006331730000965763, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005325859999629756, "count": 1, "is_parallel": true, "self": 0.0005325859999629756 }, "communicator.exchange": { "total": 0.05353253699991001, "count": 1, "is_parallel": true, "self": 0.05353253699991001 }, "steps_from_proto": { "total": 0.0018106149998402543, "count": 1, "is_parallel": true, "self": 0.00040332099933948484, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014072940005007695, "count": 8, "is_parallel": true, "self": 0.0014072940005007695 } } } } } } }, "UnityEnvironment.step": { "total": 680.1767737299738, "count": 31612, "is_parallel": true, "self": 18.435889817903217, "children": { "UnityEnvironment._generate_step_input": { "total": 12.840115173006325, "count": 31612, "is_parallel": true, "self": 12.840115173006325 }, "communicator.exchange": { "total": 587.6112231880159, "count": 31612, "is_parallel": true, "self": 587.6112231880159 }, "steps_from_proto": { "total": 61.28954555104838, "count": 31612, "is_parallel": true, "self": 12.324371044061081, "children": { "_process_rank_one_or_two_observation": { "total": 48.965174506987296, "count": 252896, "is_parallel": true, "self": 48.965174506987296 } } } } } } } } } } }, "trainer_advance": { "total": 330.57263881497215, "count": 31613, "self": 1.2669465959668287, "children": { "process_trajectory": { "total": 57.49084674600681, "count": 31613, "self": 57.38091135100649, "children": { "RLTrainer._checkpoint": { "total": 0.10993539500032057, "count": 1, "self": 0.10993539500032057 } } }, "_update_policy": { "total": 271.8148454729985, "count": 210, "self": 147.62568688400665, "children": { "TorchPPOOptimizer.update": { "total": 124.18915858899186, "count": 11415, "self": 124.18915858899186 } } } } } } }, "trainer_threads": { "total": 1.1229999472561758e-06, "count": 1, "self": 1.1229999472561758e-06 }, "TrainerController._save_models": { "total": 0.09609146899992993, "count": 1, "self": 0.0011118930001430272, "children": { "RLTrainer._checkpoint": { "total": 0.0949795759997869, "count": 1, "self": 0.0949795759997869 } } } } } } }