{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5220120549201965, "min": 0.5126771330833435, "max": 1.492493748664856, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15601.896484375, "min": 15298.28515625, "max": 45276.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29952.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24719680845737457, "min": -0.11391686648130417, "max": 0.3106386065483093, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 64.02397155761719, "min": -27.34004783630371, "max": 80.76603698730469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005267125554382801, "min": 0.005267125554382801, "max": 0.2093479484319687, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.3641855716705322, "min": 1.3641855716705322, "max": 50.243507385253906, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06995379738599332, "min": 0.06622164899978007, "max": 0.07444704377206353, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9793531634039064, "min": 0.4849271037670698, "max": 1.0527333028228751, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00998160583607774, "min": 0.00011332842470164211, "max": 0.011717497330230092, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.13974248170508835, "min": 0.0014732695211213474, "max": 0.17576245995345138, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.354426119985711e-06, "min": 7.354426119985711e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010296196567979995, "min": 0.00010296196567979995, "max": 0.0033768187743938006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245144285714285, "min": 0.10245144285714285, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343202, "min": 1.3691136000000002, "max": 2.4256062, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002548991414285714, "min": 0.0002548991414285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035685879799999994, "min": 0.0035685879799999994, "max": 0.11257805938, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0109518738463521, "min": 0.01087829191237688, "max": 0.3774993121623993, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15332622826099396, "min": 0.15229608118534088, "max": 2.6424951553344727, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 551.1153846153846, "min": 545.074074074074, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28658.0, "min": 15984.0, "max": 32730.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0523293906567144, "min": -1.0000000521540642, "max": 1.0523293906567144, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 53.66879892349243, "min": -32.000001668930054, "max": 56.559998609125614, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0523293906567144, "min": -1.0000000521540642, "max": 1.0523293906567144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 53.66879892349243, "min": -32.000001668930054, "max": 56.559998609125614, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06370741601430756, "min": 0.061470585636521316, "max": 7.256573970429599, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2490782167296857, "min": 3.2490782167296857, "max": 116.10518352687359, "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": "1703175841", "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": "1703178021" }, "total": 2180.8495752979998, "count": 1, "self": 0.7407979329996124, "children": { "run_training.setup": { "total": 0.04924006199996711, "count": 1, "self": 0.04924006199996711 }, "TrainerController.start_learning": { "total": 2180.059537303, "count": 1, "self": 1.5055777190109438, "children": { "TrainerController._reset_env": { "total": 3.084644322000031, "count": 1, "self": 3.084644322000031 }, "TrainerController.advance": { "total": 2175.341901868989, "count": 63365, "self": 1.5696453689743066, "children": { "env_step": { "total": 1523.3421550749933, "count": 63365, "self": 1382.6798618390033, "children": { "SubprocessEnvManager._take_step": { "total": 139.71468713098432, "count": 63365, "self": 5.075888066012112, "children": { "TorchPolicy.evaluate": { "total": 134.6387990649722, "count": 62572, "self": 134.6387990649722 } } }, "workers": { "total": 0.9476061050057183, "count": 63365, "self": 0.0, "children": { "worker_root": { "total": 2174.343248028003, "count": 63365, "is_parallel": true, "self": 922.467180193049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003898826000011013, "count": 1, "is_parallel": true, "self": 0.0026457970000706155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012530289999403976, "count": 8, "is_parallel": true, "self": 0.0012530289999403976 } } }, "UnityEnvironment.step": { "total": 0.05332855200003905, "count": 1, "is_parallel": true, "self": 0.0006084620000592622, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005378409999821088, "count": 1, "is_parallel": true, "self": 0.0005378409999821088 }, "communicator.exchange": { "total": 0.05051028899998755, "count": 1, "is_parallel": true, "self": 0.05051028899998755 }, "steps_from_proto": { "total": 0.001671960000010131, "count": 1, "is_parallel": true, "self": 0.00034310700004880346, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013288529999613274, "count": 8, "is_parallel": true, "self": 0.0013288529999613274 } } } } } } }, "UnityEnvironment.step": { "total": 1251.876067834954, "count": 63364, "is_parallel": true, "self": 37.10952919692181, "children": { "UnityEnvironment._generate_step_input": { "total": 26.328130384995575, "count": 63364, "is_parallel": true, "self": 26.328130384995575 }, "communicator.exchange": { "total": 1081.4985036990286, "count": 63364, "is_parallel": true, "self": 1081.4985036990286 }, "steps_from_proto": { "total": 106.93990455400808, "count": 63364, "is_parallel": true, "self": 21.768869086986854, "children": { "_process_rank_one_or_two_observation": { "total": 85.17103546702123, "count": 506912, "is_parallel": true, "self": 85.17103546702123 } } } } } } } } } } }, "trainer_advance": { "total": 650.4301014250215, "count": 63365, "self": 2.885306323972486, "children": { "process_trajectory": { "total": 132.02807670504745, "count": 63365, "self": 131.79353632904764, "children": { "RLTrainer._checkpoint": { "total": 0.23454037599981348, "count": 2, "self": 0.23454037599981348 } } }, "_update_policy": { "total": 515.5167183960016, "count": 444, "self": 310.4931097229745, "children": { "TorchPPOOptimizer.update": { "total": 205.02360867302707, "count": 22782, "self": 205.02360867302707 } } } } } } }, "trainer_threads": { "total": 1.3379999472817872e-06, "count": 1, "self": 1.3379999472817872e-06 }, "TrainerController._save_models": { "total": 0.12741205500014985, "count": 1, "self": 0.0020019019998471776, "children": { "RLTrainer._checkpoint": { "total": 0.12541015300030267, "count": 1, "self": 0.12541015300030267 } } } } } } }