{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.326950341463089, "min": 0.3174233138561249, "max": 1.4329593181610107, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9792.81640625, "min": 9553.171875, "max": 43470.25390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6591793894767761, "min": -0.19202831387519836, "max": 0.7046499252319336, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 193.13955688476562, "min": -45.510711669921875, "max": 204.82191467285156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.014648598618805408, "min": -0.020073240622878075, "max": 0.23948360979557037, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.292039394378662, "min": -5.0584564208984375, "max": 57.95503234863281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0668691588665655, "min": 0.06559629330021324, "max": 0.07277904811439476, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9361682241319169, "min": 0.48262447918947227, "max": 1.0529391999880318, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01726254585584011, "min": 0.00022079523540326307, "max": 0.018263577823832054, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24167564198176156, "min": 0.002649542824839157, "max": 0.25569008953364875, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.3811475396500005e-06, "min": 7.3811475396500005e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001033360655551, "min": 0.0001033360655551, "max": 0.0033788045737318997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246034999999998, "min": 0.10246034999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344448999999997, "min": 1.3886848, "max": 2.5262681000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025578896500000006, "min": 0.00025578896500000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003581045510000001, "min": 0.003581045510000001, "max": 0.11265418319000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010848228819668293, "min": 0.010768105275928974, "max": 0.36859115958213806, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15187519788742065, "min": 0.15187519788742065, "max": 2.5801382064819336, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 275.7383177570093, "min": 269.0892857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29504.0, "min": 15984.0, "max": 32905.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7055814682885453, "min": -1.0000000521540642, "max": 1.713049987863217, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 184.2027985751629, "min": -31.996801659464836, "max": 193.57179826498032, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7055814682885453, "min": -1.0000000521540642, "max": 1.713049987863217, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 184.2027985751629, "min": -31.996801659464836, "max": 193.57179826498032, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03069189764829827, "min": 0.030037721982807852, "max": 7.071505197323859, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.314724946016213, "min": 3.1599544174969196, "max": 113.14408315718174, "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": "1778013634", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/javij/rl-hf-course/.venv-mlagents310/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": "1778015305" }, "total": 1671.2465053209999, "count": 1, "self": 0.26931290900029126, "children": { "run_training.setup": { "total": 0.018491495000489522, "count": 1, "self": 0.018491495000489522 }, "TrainerController.start_learning": { "total": 1670.958700916999, "count": 1, "self": 1.0633043902034842, "children": { "TrainerController._reset_env": { "total": 2.128374433999852, "count": 1, "self": 2.128374433999852 }, "TrainerController.advance": { "total": 1667.685306045796, "count": 64302, "self": 0.9395110448294872, "children": { "env_step": { "total": 972.2156303431784, "count": 64302, "self": 773.4676823979989, "children": { "SubprocessEnvManager._take_step": { "total": 198.08443278213235, "count": 64302, "self": 2.722146914949917, "children": { "TorchPolicy.evaluate": { "total": 195.36228586718244, "count": 62566, "self": 195.36228586718244 } } }, "workers": { "total": 0.6635151630471228, "count": 64302, "self": 0.0, "children": { "worker_root": { "total": 1668.4554395721261, "count": 64302, "is_parallel": true, "self": 956.4840547172007, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014748329995200038, "count": 1, "is_parallel": true, "self": 0.0005038250001234701, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009710079993965337, "count": 8, "is_parallel": true, "self": 0.0009710079993965337 } } }, "UnityEnvironment.step": { "total": 0.0280242079988966, "count": 1, "is_parallel": true, "self": 0.00019692799833137542, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022987699958321173, "count": 1, "is_parallel": true, "self": 0.00022987699958321173 }, "communicator.exchange": { "total": 0.027022600001146202, "count": 1, "is_parallel": true, "self": 0.027022600001146202 }, "steps_from_proto": { "total": 0.0005748029998358106, "count": 1, "is_parallel": true, "self": 0.00015268800052581355, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004221149993099971, "count": 8, "is_parallel": true, "self": 0.0004221149993099971 } } } } } } }, "UnityEnvironment.step": { "total": 711.9713848549254, "count": 64301, "is_parallel": true, "self": 12.806162832916016, "children": { "UnityEnvironment._generate_step_input": { "total": 8.451609439165622, "count": 64301, "is_parallel": true, "self": 8.451609439165622 }, "communicator.exchange": { "total": 655.8673288118098, "count": 64301, "is_parallel": true, "self": 655.8673288118098 }, "steps_from_proto": { "total": 34.846283771033995, "count": 64301, "is_parallel": true, "self": 8.43398944196997, "children": { "_process_rank_one_or_two_observation": { "total": 26.412294329064025, "count": 514408, "is_parallel": true, "self": 26.412294329064025 } } } } } } } } } } }, "trainer_advance": { "total": 694.5301646577882, "count": 64302, "self": 1.8509094566852582, "children": { "process_trajectory": { "total": 106.37435727508819, "count": 64302, "self": 106.20453728808934, "children": { "RLTrainer._checkpoint": { "total": 0.1698199869988457, "count": 2, "self": 0.1698199869988457 } } }, "_update_policy": { "total": 586.3048979260147, "count": 455, "self": 238.0628632890075, "children": { "TorchPPOOptimizer.update": { "total": 348.24203463700724, "count": 22788, "self": 348.24203463700724 } } } } } } }, "trainer_threads": { "total": 6.900008884258568e-07, "count": 1, "self": 6.900008884258568e-07 }, "TrainerController._save_models": { "total": 0.08171535699875676, "count": 1, "self": 0.0015780619978613686, "children": { "RLTrainer._checkpoint": { "total": 0.08013729500089539, "count": 1, "self": 0.08013729500089539 } } } } } } }