{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3303144574165344, "min": 0.3303144574165344, "max": 1.484639286994934, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10030.9892578125, "min": 10030.9892578125, "max": 45038.015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989985.0, "min": 29952.0, "max": 989985.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5210311412811279, "min": -0.11293821781873703, "max": 0.602743923664093, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.7625274658203, "min": -27.105173110961914, "max": 171.1792755126953, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009394499473273754, "min": -0.0655176192522049, "max": 0.22605787217617035, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.5740928649902344, "min": -17.10009765625, "max": 54.25389099121094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06640571787783318, "min": 0.06492788642834017, "max": 0.07369663147182408, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9296800502896646, "min": 0.4773860727667664, "max": 1.0317528406055372, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015483248966094822, "min": 0.0006500025999891933, "max": 0.017837230716314583, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2167654855253275, "min": 0.007713296242536149, "max": 0.26755846074471873, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.402854675271423e-06, "min": 7.402854675271423e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010363996545379993, "min": 0.00010363996545379993, "max": 0.0035071640309454, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246758571428571, "min": 0.10246758571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345462, "min": 1.3691136000000002, "max": 2.5690546000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002565118128571427, "min": 0.0002565118128571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003591165379999998, "min": 0.003591165379999998, "max": 0.11692855454000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012451660819351673, "min": 0.012451660819351673, "max": 0.3504374921321869, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17432324588298798, "min": 0.17432324588298798, "max": 2.4530625343322754, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 374.5769230769231, "min": 303.42857142857144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29217.0, "min": 15984.0, "max": 32990.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5717688097388713, "min": -1.0000000521540642, "max": 1.6557448792214295, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.0261983498931, "min": -32.000001668930054, "max": 162.2629981637001, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5717688097388713, "min": -1.0000000521540642, "max": 1.6557448792214295, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.0261983498931, "min": -32.000001668930054, "max": 162.2629981637001, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04840788175318845, "min": 0.04153138886512451, "max": 6.781635235063732, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.727406894995511, "min": 3.727406894995511, "max": 108.5061637610197, "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": "1783818954", "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": "1783821339" }, "total": 2384.8509445409995, "count": 1, "self": 0.5311091919998034, "children": { "run_training.setup": { "total": 0.023644015999707335, "count": 1, "self": 0.023644015999707335 }, "TrainerController.start_learning": { "total": 2384.296191333, "count": 1, "self": 1.4678509111054154, "children": { "TrainerController._reset_env": { "total": 2.5155557519997274, "count": 1, "self": 2.5155557519997274 }, "TrainerController.advance": { "total": 2380.2358617908944, "count": 63768, "self": 1.4682368958829102, "children": { "env_step": { "total": 1749.450461289981, "count": 63768, "self": 1591.7332020179438, "children": { "SubprocessEnvManager._take_step": { "total": 156.8185237839716, "count": 63768, "self": 4.773340211954292, "children": { "TorchPolicy.evaluate": { "total": 152.04518357201732, "count": 62565, "self": 152.04518357201732 } } }, "workers": { "total": 0.8987354880655403, "count": 63768, "self": 0.0, "children": { "worker_root": { "total": 2378.370366294977, "count": 63768, "is_parallel": true, "self": 908.4712261120003, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002283114999954705, "count": 1, "is_parallel": true, "self": 0.0006979740001042956, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015851409998504096, "count": 8, "is_parallel": true, "self": 0.0015851409998504096 } } }, "UnityEnvironment.step": { "total": 0.1302204730000085, "count": 1, "is_parallel": true, "self": 0.000529461999576597, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004329340004005644, "count": 1, "is_parallel": true, "self": 0.0004329340004005644 }, "communicator.exchange": { "total": 0.12350311799991687, "count": 1, "is_parallel": true, "self": 0.12350311799991687 }, "steps_from_proto": { "total": 0.005754959000114468, "count": 1, "is_parallel": true, "self": 0.0003818690001935465, "children": { "_process_rank_one_or_two_observation": { "total": 0.005373089999920921, "count": 8, "is_parallel": true, "self": 0.005373089999920921 } } } } } } }, "UnityEnvironment.step": { "total": 1469.8991401829767, "count": 63767, "is_parallel": true, "self": 34.18902452879547, "children": { "UnityEnvironment._generate_step_input": { "total": 24.012195656192034, "count": 63767, "is_parallel": true, "self": 24.012195656192034 }, "communicator.exchange": { "total": 1300.1779641460134, "count": 63767, "is_parallel": true, "self": 1300.1779641460134 }, "steps_from_proto": { "total": 111.51995585197574, "count": 63767, "is_parallel": true, "self": 23.42131923775014, "children": { "_process_rank_one_or_two_observation": { "total": 88.0986366142256, "count": 510136, "is_parallel": true, "self": 88.0986366142256 } } } } } } } } } } }, "trainer_advance": { "total": 629.3171636050306, "count": 63768, "self": 2.6886928120707125, "children": { "process_trajectory": { "total": 109.2336006689452, "count": 63768, "self": 109.04065439294527, "children": { "RLTrainer._checkpoint": { "total": 0.19294627599992964, "count": 2, "self": 0.19294627599992964 } } }, "_update_policy": { "total": 517.3948701240147, "count": 446, "self": 276.55039621705873, "children": { "TorchPPOOptimizer.update": { "total": 240.84447390695595, "count": 22812, "self": 240.84447390695595 } } } } } } }, "trainer_threads": { "total": 8.900005923351273e-07, "count": 1, "self": 8.900005923351273e-07 }, "TrainerController._save_models": { "total": 0.0769219889998567, "count": 1, "self": 0.0012016000000585336, "children": { "RLTrainer._checkpoint": { "total": 0.07572038899979816, "count": 1, "self": 0.07572038899979816 } } } } } } }