{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45982417464256287, "min": 0.451816588640213, "max": 1.4711294174194336, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13743.224609375, "min": 13605.1015625, "max": 44628.18359375, "count": 33 }, "Pyramids.Step.mean": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989992.0, "min": 29952.0, "max": 989992.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4764930009841919, "min": -0.08142147213220596, "max": 0.5113253593444824, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 127.70012664794922, "min": -19.541152954101562, "max": 140.1031494140625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01981690339744091, "min": 0.010558750480413437, "max": 0.4067944288253784, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.310930252075195, "min": 2.6408042907714844, "max": 96.4102783203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07000386397287782, "min": 0.06642347967066424, "max": 0.07422039198745703, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9800540956202894, "min": 0.47577493339251786, "max": 1.0466420093560407, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012512954195352949, "min": 0.000627352855187124, "max": 0.015128764340989727, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17518135873494128, "min": 0.004391469986309868, "max": 0.21180270077385618, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.66319030277857e-06, "min": 7.66319030277857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010728466423889999, "min": 0.00010728466423889999, "max": 0.0035069636310121996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025543642857143, "min": 0.1025543642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357611000000001, "min": 1.3691136000000002, "max": 2.5689878, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002651809921428572, "min": 0.0002651809921428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003712533890000001, "min": 0.003712533890000001, "max": 0.11692188122, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011425274424254894, "min": 0.011425274424254894, "max": 0.38322964310646057, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15995384752750397, "min": 0.15995384752750397, "max": 2.682607412338257, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.7894736842105, "min": 349.1058823529412, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29852.0, "min": 15984.0, "max": 33524.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4190933086474737, "min": -1.0000000521540642, "max": 1.539111369489869, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.43199814856052, "min": -32.000001668930054, "max": 128.3221983537078, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4190933086474737, "min": -1.0000000521540642, "max": 1.539111369489869, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.43199814856052, "min": -32.000001668930054, "max": 128.3221983537078, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04649649310255578, "min": 0.04332623382046329, "max": 7.08379302918911, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.487236982691684, "min": 3.487236982691684, "max": 113.34068846702576, "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": "1683133806", "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=Pyramids Training --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": "1683135989" }, "total": 2182.430048054, "count": 1, "self": 0.4854135010000391, "children": { "run_training.setup": { "total": 0.043035613000029116, "count": 1, "self": 0.043035613000029116 }, "TrainerController.start_learning": { "total": 2181.90159894, "count": 1, "self": 1.4138936029517026, "children": { "TrainerController._reset_env": { "total": 4.718134125000006, "count": 1, "self": 4.718134125000006 }, "TrainerController.advance": { "total": 2175.6476735690485, "count": 63607, "self": 1.4907823910371008, "children": { "env_step": { "total": 1543.9166333609996, "count": 63607, "self": 1428.7986671110261, "children": { "SubprocessEnvManager._take_step": { "total": 114.26029547199641, "count": 63607, "self": 4.8508481320285455, "children": { "TorchPolicy.evaluate": { "total": 109.40944733996787, "count": 62564, "self": 109.40944733996787 } } }, "workers": { "total": 0.8576707779769777, "count": 63607, "self": 0.0, "children": { "worker_root": { "total": 2176.7286943760296, "count": 63607, "is_parallel": true, "self": 865.1904171400934, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004736227000080362, "count": 1, "is_parallel": true, "self": 0.0035435380001445083, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011926889999358536, "count": 8, "is_parallel": true, "self": 0.0011926889999358536 } } }, "UnityEnvironment.step": { "total": 0.07776320499999656, "count": 1, "is_parallel": true, "self": 0.000634054000101969, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004682109999976092, "count": 1, "is_parallel": true, "self": 0.0004682109999976092 }, "communicator.exchange": { "total": 0.07483952299992325, "count": 1, "is_parallel": true, "self": 0.07483952299992325 }, "steps_from_proto": { "total": 0.001821416999973735, "count": 1, "is_parallel": true, "self": 0.000444880999907582, "children": { "_process_rank_one_or_two_observation": { "total": 0.001376536000066153, "count": 8, "is_parallel": true, "self": 0.001376536000066153 } } } } } } }, "UnityEnvironment.step": { "total": 1311.5382772359362, "count": 63606, "is_parallel": true, "self": 32.33994220791237, "children": { "UnityEnvironment._generate_step_input": { "total": 23.554881789989395, "count": 63606, "is_parallel": true, "self": 23.554881789989395 }, "communicator.exchange": { "total": 1154.5345770009899, "count": 63606, "is_parallel": true, "self": 1154.5345770009899 }, "steps_from_proto": { "total": 101.10887623704468, "count": 63606, "is_parallel": true, "self": 21.17766155810682, "children": { "_process_rank_one_or_two_observation": { "total": 79.93121467893786, "count": 508848, "is_parallel": true, "self": 79.93121467893786 } } } } } } } } } } }, "trainer_advance": { "total": 630.2402578170119, "count": 63607, "self": 2.6183805349608065, "children": { "process_trajectory": { "total": 107.92745304905043, "count": 63607, "self": 107.70911411405018, "children": { "RLTrainer._checkpoint": { "total": 0.21833893500024715, "count": 2, "self": 0.21833893500024715 } } }, "_update_policy": { "total": 519.6944242330006, "count": 439, "self": 335.24648306595316, "children": { "TorchPPOOptimizer.update": { "total": 184.44794116704747, "count": 22806, "self": 184.44794116704747 } } } } } } }, "trainer_threads": { "total": 9.000000318337698e-07, "count": 1, "self": 9.000000318337698e-07 }, "TrainerController._save_models": { "total": 0.12189674299997932, "count": 1, "self": 0.0013831569999638305, "children": { "RLTrainer._checkpoint": { "total": 0.1205135860000155, "count": 1, "self": 0.1205135860000155 } } } } } } }