{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43048590421676636, "min": 0.43048590421676636, "max": 1.4206033945083618, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12900.8017578125, "min": 12857.025390625, "max": 43095.42578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29893.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29893.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5001581907272339, "min": -0.11593702435493469, "max": 0.6160997152328491, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 135.54286193847656, "min": -27.94082260131836, "max": 173.7401123046875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.00434536999091506, "min": -0.023226678371429443, "max": 0.3599995970726013, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.1775952577590942, "min": -6.4105634689331055, "max": 85.67990112304688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07128555288072674, "min": 0.06382248763840113, "max": 0.0729491203526558, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.069283293210901, "min": 0.469455201739456, "max": 1.069283293210901, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01468030995909228, "min": 7.335998513852361e-05, "max": 0.017150374080215223, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2202046493863842, "min": 0.0010270397919393305, "max": 0.24010523712301313, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.424937525053335e-06, "min": 7.424937525053335e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011137406287580002, "min": 0.00011137406287580002, "max": 0.0033825668724777993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247494666666666, "min": 0.10247494666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371242, "min": 1.3886848, "max": 2.5275222, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025724717200000007, "min": 0.00025724717200000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003858707580000001, "min": 0.003858707580000001, "max": 0.11277946778000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012858767993748188, "min": 0.012858767993748188, "max": 0.44626113772392273, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1928815245628357, "min": 0.18697506189346313, "max": 3.1238279342651367, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.30864197530866, "min": 332.6931818181818, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30643.0, "min": 17587.0, "max": 32971.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.547604916824235, "min": -0.999973385532697, "max": 1.643363024553527, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 125.35599826276302, "min": -31.99640165269375, "max": 151.18939825892448, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.547604916824235, "min": -0.999973385532697, "max": 1.643363024553527, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 125.35599826276302, "min": -31.99640165269375, "max": 151.18939825892448, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05067506781599576, "min": 0.048126506717219145, "max": 8.155301230442193, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.104680493095657, "min": 3.9703685331041925, "max": 146.79542214795947, "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": "1743637863", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1743640399" }, "total": 2536.047659891, "count": 1, "self": 0.8843261140000322, "children": { "run_training.setup": { "total": 0.021870323000030112, "count": 1, "self": 0.021870323000030112 }, "TrainerController.start_learning": { "total": 2535.1414634539997, "count": 1, "self": 1.8841465579653232, "children": { "TrainerController._reset_env": { "total": 3.0696945150000374, "count": 1, "self": 3.0696945150000374 }, "TrainerController.advance": { "total": 2530.049438693033, "count": 63753, "self": 2.1209658760208185, "children": { "env_step": { "total": 1769.5816260650115, "count": 63753, "self": 1576.4920868429876, "children": { "SubprocessEnvManager._take_step": { "total": 191.99298355098904, "count": 63753, "self": 5.7257910690359495, "children": { "TorchPolicy.evaluate": { "total": 186.2671924819531, "count": 62575, "self": 186.2671924819531 } } }, "workers": { "total": 1.096555671034821, "count": 63753, "self": 0.0, "children": { "worker_root": { "total": 2528.5614226659586, "count": 63753, "is_parallel": true, "self": 1091.5797361679922, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002516823999940243, "count": 1, "is_parallel": true, "self": 0.0007245439996950154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017922800002452277, "count": 8, "is_parallel": true, "self": 0.0017922800002452277 } } }, "UnityEnvironment.step": { "total": 0.04944326000008914, "count": 1, "is_parallel": true, "self": 0.0005867530003342836, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005047749998539075, "count": 1, "is_parallel": true, "self": 0.0005047749998539075 }, "communicator.exchange": { "total": 0.04677834799986158, "count": 1, "is_parallel": true, "self": 0.04677834799986158 }, "steps_from_proto": { "total": 0.0015733840000393684, "count": 1, "is_parallel": true, "self": 0.0003333000004204223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012400839996189461, "count": 8, "is_parallel": true, "self": 0.0012400839996189461 } } } } } } }, "UnityEnvironment.step": { "total": 1436.9816864979664, "count": 63752, "is_parallel": true, "self": 37.49685541297731, "children": { "UnityEnvironment._generate_step_input": { "total": 25.513120493989163, "count": 63752, "is_parallel": true, "self": 25.513120493989163 }, "communicator.exchange": { "total": 1266.0741577909441, "count": 63752, "is_parallel": true, "self": 1266.0741577909441 }, "steps_from_proto": { "total": 107.89755280005579, "count": 63752, "is_parallel": true, "self": 23.082978630985735, "children": { "_process_rank_one_or_two_observation": { "total": 84.81457416907006, "count": 510016, "is_parallel": true, "self": 84.81457416907006 } } } } } } } } } } }, "trainer_advance": { "total": 758.3468467520006, "count": 63753, "self": 3.6249706990085997, "children": { "process_trajectory": { "total": 140.4497918879913, "count": 63753, "self": 140.1635398079918, "children": { "RLTrainer._checkpoint": { "total": 0.28625207999948543, "count": 2, "self": 0.28625207999948543 } } }, "_update_policy": { "total": 614.2720841650007, "count": 450, "self": 339.2316469060222, "children": { "TorchPPOOptimizer.update": { "total": 275.0404372589785, "count": 22779, "self": 275.0404372589785 } } } } } } }, "trainer_threads": { "total": 1.6930007404880598e-06, "count": 1, "self": 1.6930007404880598e-06 }, "TrainerController._save_models": { "total": 0.13818199500019546, "count": 1, "self": 0.0023244600006364635, "children": { "RLTrainer._checkpoint": { "total": 0.135857534999559, "count": 1, "self": 0.135857534999559 } } } } } } }