{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4451207220554352, "min": 0.4323638379573822, "max": 1.4104468822479248, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13474.6943359375, "min": 12901.7373046875, "max": 42787.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989915.0, "min": 29952.0, "max": 989915.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4584326446056366, "min": -0.09862297028303146, "max": 0.4658299386501312, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 122.85994720458984, "min": -23.76813507080078, "max": 125.77408599853516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02424754947423935, "min": -0.002871707547456026, "max": 0.42462682723999023, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.498343467712402, "min": -0.7495156526565552, "max": 100.63655853271484, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06379665283159176, "min": 0.06379665283159176, "max": 0.07497356959267089, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8931531396422846, "min": 0.5093815884654592, "max": 1.03170840026966, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0137657374538581, "min": 0.0006889801874042434, "max": 0.01496940388121099, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1927203243540134, "min": 0.00869785353446703, "max": 0.22454105821816486, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.587247470949996e-06, "min": 7.587247470949996e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010622146459329995, "min": 0.00010622146459329995, "max": 0.0036332626889125, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252905000000002, "min": 0.10252905000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354067000000004, "min": 1.3691136000000002, "max": 2.6110875000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626520949999999, "min": 0.0002626520949999999, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003677129329999998, "min": 0.003677129329999998, "max": 0.12112764125, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014423089101910591, "min": 0.014423089101910591, "max": 0.518326461315155, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20192325115203857, "min": 0.20192325115203857, "max": 3.6282851696014404, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.4142857142857, "min": 403.5890410958904, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30479.0, "min": 15984.0, "max": 33041.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.421697122497218, "min": -1.0000000521540642, "max": 1.4910621429617341, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 99.51879857480526, "min": -32.000001668930054, "max": 110.33859857916832, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.421697122497218, "min": -1.0000000521540642, "max": 1.4910621429617341, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 99.51879857480526, "min": -32.000001668930054, "max": 110.33859857916832, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06517311317750552, "min": 0.06517311317750552, "max": 10.364394264295697, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.5621179224253865, "min": 4.5621179224253865, "max": 165.83030822873116, "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": "1709089732", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709091855" }, "total": 2123.145726284, "count": 1, "self": 0.5398666719997891, "children": { "run_training.setup": { "total": 0.0464521460000924, "count": 1, "self": 0.0464521460000924 }, "TrainerController.start_learning": { "total": 2122.559407466, "count": 1, "self": 1.3442305229868907, "children": { "TrainerController._reset_env": { "total": 2.340669458999855, "count": 1, "self": 2.340669458999855 }, "TrainerController.advance": { "total": 2118.7812866140134, "count": 63605, "self": 1.4240191070307446, "children": { "env_step": { "total": 1499.6670341349782, "count": 63605, "self": 1367.3890129801177, "children": { "SubprocessEnvManager._take_step": { "total": 131.42935862894433, "count": 63605, "self": 4.751789223934338, "children": { "TorchPolicy.evaluate": { "total": 126.67756940500999, "count": 62559, "self": 126.67756940500999 } } }, "workers": { "total": 0.8486625259160974, "count": 63605, "self": 0.0, "children": { "worker_root": { "total": 2117.38368223095, "count": 63605, "is_parallel": true, "self": 866.530925944028, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020558799999434996, "count": 1, "is_parallel": true, "self": 0.0006778010001653456, "children": { "_process_rank_one_or_two_observation": { "total": 0.001378078999778154, "count": 8, "is_parallel": true, "self": 0.001378078999778154 } } }, "UnityEnvironment.step": { "total": 0.08226506699998026, "count": 1, "is_parallel": true, "self": 0.0005873489999430603, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005070069998964755, "count": 1, "is_parallel": true, "self": 0.0005070069998964755 }, "communicator.exchange": { "total": 0.07956326500016075, "count": 1, "is_parallel": true, "self": 0.07956326500016075 }, "steps_from_proto": { "total": 0.0016074459999799728, "count": 1, "is_parallel": true, "self": 0.0003253189997849404, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012821270001950325, "count": 8, "is_parallel": true, "self": 0.0012821270001950325 } } } } } } }, "UnityEnvironment.step": { "total": 1250.852756286922, "count": 63604, "is_parallel": true, "self": 35.03816136479668, "children": { "UnityEnvironment._generate_step_input": { "total": 25.31926580903678, "count": 63604, "is_parallel": true, "self": 25.31926580903678 }, "communicator.exchange": { "total": 1088.0278370480157, "count": 63604, "is_parallel": true, "self": 1088.0278370480157 }, "steps_from_proto": { "total": 102.46749206507275, "count": 63604, "is_parallel": true, "self": 20.60328916399567, "children": { "_process_rank_one_or_two_observation": { "total": 81.86420290107708, "count": 508832, "is_parallel": true, "self": 81.86420290107708 } } } } } } } } } } }, "trainer_advance": { "total": 617.6902333720047, "count": 63605, "self": 2.65248893404123, "children": { "process_trajectory": { "total": 126.25097332096152, "count": 63605, "self": 126.04691674396122, "children": { "RLTrainer._checkpoint": { "total": 0.20405657700030133, "count": 2, "self": 0.20405657700030133 } } }, "_update_policy": { "total": 488.786771117002, "count": 450, "self": 287.23869353602004, "children": { "TorchPPOOptimizer.update": { "total": 201.54807758098195, "count": 22815, "self": 201.54807758098195 } } } } } } }, "trainer_threads": { "total": 1.1399997674743645e-06, "count": 1, "self": 1.1399997674743645e-06 }, "TrainerController._save_models": { "total": 0.09321972999987338, "count": 1, "self": 0.0015148270003919606, "children": { "RLTrainer._checkpoint": { "total": 0.09170490299948142, "count": 1, "self": 0.09170490299948142 } } } } } } }