{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3490028977394104, "min": 0.3490028977394104, "max": 1.5002765655517578, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10313.7333984375, "min": 10313.7333984375, "max": 45512.390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3843599855899811, "min": -0.14145436882972717, "max": 0.4473913311958313, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 99.93359375, "min": -33.94904708862305, "max": 121.24304962158203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013444162905216217, "min": -0.010150044225156307, "max": 0.5924503803253174, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.4954824447631836, "min": -2.5578112602233887, "max": 140.41073608398438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06755112477029408, "min": 0.06432348161026659, "max": 0.07349624312658641, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9457157467841171, "min": 0.5144737018861049, "max": 1.0323032667083145, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015232850942820298, "min": 0.0008376009070016619, "max": 0.015232850942820298, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21325991319948417, "min": 0.00837600907001662, "max": 0.22411914748555123, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.709733144407142e-06, "min": 7.709733144407142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001079362640217, "min": 0.0001079362640217, "max": 0.0035081240306254003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256987857142856, "min": 0.10256987857142856, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359783, "min": 1.3886848, "max": 2.5693746, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026673086928571423, "min": 0.00026673086928571423, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037342321699999994, "min": 0.0037342321699999994, "max": 0.11696052254, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015443922020494938, "min": 0.015443922020494938, "max": 0.6668349504470825, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21621491014957428, "min": 0.21621491014957428, "max": 4.667844772338867, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 455.6307692307692, "min": 404.9142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29616.0, "min": 15984.0, "max": 33354.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3660605830902404, "min": -1.0000000521540642, "max": 1.4483323688028564, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.15999848395586, "min": -30.999201618134975, "max": 102.8315981850028, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3660605830902404, "min": -1.0000000521540642, "max": 1.4483323688028564, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.15999848395586, "min": -30.999201618134975, "max": 102.8315981850028, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07237672993108969, "min": 0.07048407845847708, "max": 13.606595835648477, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.776864175451919, "min": 4.776864175451919, "max": 217.70553337037563, "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": "1740642738", "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": "1740644815" }, "total": 2077.6411050710003, "count": 1, "self": 0.7310277990000031, "children": { "run_training.setup": { "total": 0.02015310199999476, "count": 1, "self": 0.02015310199999476 }, "TrainerController.start_learning": { "total": 2076.88992417, "count": 1, "self": 1.1532665509566868, "children": { "TrainerController._reset_env": { "total": 2.418771798999842, "count": 1, "self": 2.418771798999842 }, "TrainerController.advance": { "total": 2073.198000866044, "count": 63624, "self": 1.239706204142749, "children": { "env_step": { "total": 1416.6882651508977, "count": 63624, "self": 1274.1472422438158, "children": { "SubprocessEnvManager._take_step": { "total": 141.8671150080679, "count": 63624, "self": 4.428074222119903, "children": { "TorchPolicy.evaluate": { "total": 137.439040785948, "count": 62552, "self": 137.439040785948 } } }, "workers": { "total": 0.6739078990140115, "count": 63624, "self": 0.0, "children": { "worker_root": { "total": 2072.3051315729426, "count": 63624, "is_parallel": true, "self": 899.1633680768853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019374380001409008, "count": 1, "is_parallel": true, "self": 0.0006278690000272036, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013095690001136973, "count": 8, "is_parallel": true, "self": 0.0013095690001136973 } } }, "UnityEnvironment.step": { "total": 0.06787386599989986, "count": 1, "is_parallel": true, "self": 0.0004997880000701116, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046138699985931453, "count": 1, "is_parallel": true, "self": 0.00046138699985931453 }, "communicator.exchange": { "total": 0.06531603500002348, "count": 1, "is_parallel": true, "self": 0.06531603500002348 }, "steps_from_proto": { "total": 0.001596655999946961, "count": 1, "is_parallel": true, "self": 0.00033773899986044853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012589170000865124, "count": 8, "is_parallel": true, "self": 0.0012589170000865124 } } } } } } }, "UnityEnvironment.step": { "total": 1173.1417634960574, "count": 63623, "is_parallel": true, "self": 30.247557377036856, "children": { "UnityEnvironment._generate_step_input": { "total": 22.34549160599113, "count": 63623, "is_parallel": true, "self": 22.34549160599113 }, "communicator.exchange": { "total": 1030.6586164010116, "count": 63623, "is_parallel": true, "self": 1030.6586164010116 }, "steps_from_proto": { "total": 89.89009811201777, "count": 63623, "is_parallel": true, "self": 17.401386551964833, "children": { "_process_rank_one_or_two_observation": { "total": 72.48871156005293, "count": 508984, "is_parallel": true, "self": 72.48871156005293 } } } } } } } } } } }, "trainer_advance": { "total": 655.2700295110037, "count": 63624, "self": 2.304609800961316, "children": { "process_trajectory": { "total": 120.32255242204405, "count": 63624, "self": 120.07594756104368, "children": { "RLTrainer._checkpoint": { "total": 0.24660486100037815, "count": 2, "self": 0.24660486100037815 } } }, "_update_policy": { "total": 532.6428672879983, "count": 449, "self": 292.05895458601935, "children": { "TorchPPOOptimizer.update": { "total": 240.583912701979, "count": 22809, "self": 240.583912701979 } } } } } } }, "trainer_threads": { "total": 1.231999704032205e-06, "count": 1, "self": 1.231999704032205e-06 }, "TrainerController._save_models": { "total": 0.11988372199994046, "count": 1, "self": 0.0020174589999442105, "children": { "RLTrainer._checkpoint": { "total": 0.11786626299999625, "count": 1, "self": 0.11786626299999625 } } } } } } }