{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6936154365539551, "min": 0.6717783808708191, "max": 1.4610729217529297, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20875.05078125, "min": 20088.861328125, "max": 44323.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989884.0, "min": 29952.0, "max": 989884.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.28655532002449036, "min": -0.10587826371192932, "max": 0.3397061824798584, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 73.64471435546875, "min": -25.622539520263672, "max": 89.34272766113281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.08099333941936493, "min": -0.08099333941936493, "max": 0.5409696698188782, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -20.815288543701172, "min": -20.815288543701172, "max": 128.20980834960938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06706104077845036, "min": 0.06658381631963753, "max": 0.07534246302726112, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.938854570898305, "min": 0.4685908804235153, "max": 1.1045550341465666, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013075488419244288, "min": 0.0008307486712330204, "max": 0.013075488419244288, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18305683786942004, "min": 0.008992500325520862, "max": 0.18305683786942004, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.322561844892853e-06, "min": 7.322561844892853e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010251586582849995, "min": 0.00010251586582849995, "max": 0.0035065676311441993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244082142857143, "min": 0.10244082142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341715, "min": 1.3691136000000002, "max": 2.5688557999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002538380607142856, "min": 0.0002538380607142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003553732849999998, "min": 0.003553732849999998, "max": 0.11690869442000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010021538473665714, "min": 0.010021538473665714, "max": 0.5895799398422241, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14030154049396515, "min": 0.14030154049396515, "max": 4.127059459686279, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 570.68, "min": 468.48333333333335, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28534.0, "min": 15984.0, "max": 32974.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0768195761769426, "min": -1.0000000521540642, "max": 1.2981233132382235, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 54.91779838502407, "min": -32.000001668930054, "max": 77.8873987942934, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0768195761769426, "min": -1.0000000521540642, "max": 1.2981233132382235, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 54.91779838502407, "min": -32.000001668930054, "max": 77.8873987942934, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05903493688902909, "min": 0.05383786903160702, "max": 12.126244661398232, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0107817813404836, "min": 3.0107817813404836, "max": 194.0199145823717, "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": "1758791870", "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": "1758793891" }, "total": 2020.796249454, "count": 1, "self": 0.9031852439998147, "children": { "run_training.setup": { "total": 0.021864443000140454, "count": 1, "self": 0.021864443000140454 }, "TrainerController.start_learning": { "total": 2019.871199767, "count": 1, "self": 1.1913714890079063, "children": { "TrainerController._reset_env": { "total": 2.0847412240000267, "count": 1, "self": 2.0847412240000267 }, "TrainerController.advance": { "total": 2016.475920035992, "count": 63390, "self": 1.2320699650422284, "children": { "env_step": { "total": 1380.7793479829388, "count": 63390, "self": 1244.5311635379983, "children": { "SubprocessEnvManager._take_step": { "total": 135.55113946200868, "count": 63390, "self": 4.2671260460444955, "children": { "TorchPolicy.evaluate": { "total": 131.28401341596418, "count": 62560, "self": 131.28401341596418 } } }, "workers": { "total": 0.6970449829318568, "count": 63390, "self": 0.0, "children": { "worker_root": { "total": 2013.1663892779964, "count": 63390, "is_parallel": true, "self": 875.2429566390047, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019160060001013335, "count": 1, "is_parallel": true, "self": 0.000681402000509479, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012346039995918545, "count": 8, "is_parallel": true, "self": 0.0012346039995918545 } } }, "UnityEnvironment.step": { "total": 0.04715399400015485, "count": 1, "is_parallel": true, "self": 0.0005351649999738584, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047192100009851856, "count": 1, "is_parallel": true, "self": 0.00047192100009851856 }, "communicator.exchange": { "total": 0.044562197000004744, "count": 1, "is_parallel": true, "self": 0.044562197000004744 }, "steps_from_proto": { "total": 0.001584711000077732, "count": 1, "is_parallel": true, "self": 0.00032369500036111276, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012610159997166193, "count": 8, "is_parallel": true, "self": 0.0012610159997166193 } } } } } } }, "UnityEnvironment.step": { "total": 1137.9234326389917, "count": 63389, "is_parallel": true, "self": 31.727004849977675, "children": { "UnityEnvironment._generate_step_input": { "total": 21.703883245064844, "count": 63389, "is_parallel": true, "self": 21.703883245064844 }, "communicator.exchange": { "total": 986.277344611917, "count": 63389, "is_parallel": true, "self": 986.277344611917 }, "steps_from_proto": { "total": 98.21519993203219, "count": 63389, "is_parallel": true, "self": 19.91200255001604, "children": { "_process_rank_one_or_two_observation": { "total": 78.30319738201615, "count": 507112, "is_parallel": true, "self": 78.30319738201615 } } } } } } } } } } }, "trainer_advance": { "total": 634.4645020880109, "count": 63390, "self": 2.259592281991445, "children": { "process_trajectory": { "total": 115.96362715101532, "count": 63390, "self": 115.730274130015, "children": { "RLTrainer._checkpoint": { "total": 0.23335302100031186, "count": 2, "self": 0.23335302100031186 } } }, "_update_policy": { "total": 516.2412826550042, "count": 447, "self": 287.85748381399094, "children": { "TorchPPOOptimizer.update": { "total": 228.38379884101323, "count": 22842, "self": 228.38379884101323 } } } } } } }, "trainer_threads": { "total": 1.2700002116616815e-06, "count": 1, "self": 1.2700002116616815e-06 }, "TrainerController._save_models": { "total": 0.11916574799988666, "count": 1, "self": 0.0015211169998110563, "children": { "RLTrainer._checkpoint": { "total": 0.1176446310000756, "count": 1, "self": 0.1176446310000756 } } } } } } }