{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6924961805343628, "min": 0.6924961805343628, "max": 1.3966422080993652, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20852.4453125, "min": 20708.794921875, "max": 42368.5390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29942.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29942.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.46009859442710876, "min": -0.10330336540937424, "max": 0.46049025654792786, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 125.14682006835938, "min": -24.89611053466797, "max": 125.14682006835938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03080451488494873, "min": -0.03464241325855255, "max": 0.2665810286998749, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.378828048706055, "min": -9.28416633605957, "max": 64.51261138916016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07197512458133999, "min": 0.06548260628701161, "max": 0.07267732829565092, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0076517441387598, "min": 0.555548734596694, "max": 1.0478121472839905, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015905117723851628, "min": 0.0004308478736220075, "max": 0.015905117723851628, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2226716481339228, "min": 0.006031870230708105, "max": 0.2226716481339228, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.490668931714283e-06, "min": 7.490668931714283e-06, "max": 0.00029501497666167495, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010486936504399995, "min": 0.00010486936504399995, "max": 0.003757819047393699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249685714285715, "min": 0.10249685714285715, "max": 0.19833832500000004, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349560000000001, "min": 1.4349560000000001, "max": 2.6526062999999995, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002594360285714285, "min": 0.0002594360285714285, "max": 0.0098339986675, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003632104399999999, "min": 0.003632104399999999, "max": 0.12527536937, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01001888606697321, "min": 0.01001888606697321, "max": 0.41279104351997375, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14026440680027008, "min": 0.14026440680027008, "max": 3.30232834815979, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 414.36486486486484, "min": 413.2089552238806, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30663.0, "min": 16869.0, "max": 32768.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5045297144836671, "min": -0.9996870079118273, "max": 1.5270805688046698, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.33519887179136, "min": -29.7428016141057, "max": 111.33519887179136, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5045297144836671, "min": -0.9996870079118273, "max": 1.5270805688046698, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.33519887179136, "min": -29.7428016141057, "max": 111.33519887179136, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042923439042391, "min": 0.042923439042391, "max": 7.059824541211128, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1763344891369343, "min": 2.891145779954968, "max": 120.01701720058918, "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": "1684603294", "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=PyramidsTraining --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": "1684605327" }, "total": 2032.707460994, "count": 1, "self": 0.4770500929998889, "children": { "run_training.setup": { "total": 0.038115211000103955, "count": 1, "self": 0.038115211000103955 }, "TrainerController.start_learning": { "total": 2032.19229569, "count": 1, "self": 1.3490326730295692, "children": { "TrainerController._reset_env": { "total": 5.013466694999806, "count": 1, "self": 5.013466694999806 }, "TrainerController.advance": { "total": 2025.7372163759705, "count": 63404, "self": 1.3282905010594277, "children": { "env_step": { "total": 1399.588347762959, "count": 63404, "self": 1290.5757671108759, "children": { "SubprocessEnvManager._take_step": { "total": 108.22025434203988, "count": 63404, "self": 4.614100324072069, "children": { "TorchPolicy.evaluate": { "total": 103.60615401796781, "count": 62548, "self": 103.60615401796781 } } }, "workers": { "total": 0.792326310043336, "count": 63404, "self": 0.0, "children": { "worker_root": { "total": 2027.6187733599468, "count": 63404, "is_parallel": true, "self": 845.9503525709565, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024150360000021465, "count": 1, "is_parallel": true, "self": 0.0006649240001479484, "children": { "_process_rank_one_or_two_observation": { "total": 0.001750111999854198, "count": 8, "is_parallel": true, "self": 0.001750111999854198 } } }, "UnityEnvironment.step": { "total": 0.07926975999998831, "count": 1, "is_parallel": true, "self": 0.0015808830000878515, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005460259999381378, "count": 1, "is_parallel": true, "self": 0.0005460259999381378 }, "communicator.exchange": { "total": 0.0703074299999571, "count": 1, "is_parallel": true, "self": 0.0703074299999571 }, "steps_from_proto": { "total": 0.006835421000005226, "count": 1, "is_parallel": true, "self": 0.0011715029993411008, "children": { "_process_rank_one_or_two_observation": { "total": 0.005663918000664125, "count": 8, "is_parallel": true, "self": 0.005663918000664125 } } } } } } }, "UnityEnvironment.step": { "total": 1181.6684207889903, "count": 63403, "is_parallel": true, "self": 31.480100532942288, "children": { "UnityEnvironment._generate_step_input": { "total": 22.401434327014613, "count": 63403, "is_parallel": true, "self": 22.401434327014613 }, "communicator.exchange": { "total": 1031.9065440209886, "count": 63403, "is_parallel": true, "self": 1031.9065440209886 }, "steps_from_proto": { "total": 95.88034190804478, "count": 63403, "is_parallel": true, "self": 19.404424160094322, "children": { "_process_rank_one_or_two_observation": { "total": 76.47591774795046, "count": 507224, "is_parallel": true, "self": 76.47591774795046 } } } } } } } } } } }, "trainer_advance": { "total": 624.820578111952, "count": 63404, "self": 2.6352682569036006, "children": { "process_trajectory": { "total": 103.79030804204649, "count": 63404, "self": 103.58609867604673, "children": { "RLTrainer._checkpoint": { "total": 0.20420936599975903, "count": 2, "self": 0.20420936599975903 } } }, "_update_policy": { "total": 518.395001813002, "count": 456, "self": 332.1143105219876, "children": { "TorchPPOOptimizer.update": { "total": 186.28069129101436, "count": 22770, "self": 186.28069129101436 } } } } } } }, "trainer_threads": { "total": 9.150003279501107e-07, "count": 1, "self": 9.150003279501107e-07 }, "TrainerController._save_models": { "total": 0.09257903099978648, "count": 1, "self": 0.0013952999997854931, "children": { "RLTrainer._checkpoint": { "total": 0.09118373100000099, "count": 1, "self": 0.09118373100000099 } } } } } } }