{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34810778498649597, "min": 0.3432939946651459, "max": 1.4697444438934326, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10521.2099609375, "min": 10216.4296875, "max": 44586.16796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 29960.0, "max": 989994.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 29960.0, "max": 989994.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5982646346092224, "min": -0.08361122012138367, "max": 0.6975889801979065, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 167.51409912109375, "min": -20.150304794311523, "max": 205.78875732421875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03435632213950157, "min": -0.0024299276992678642, "max": 0.40612444281578064, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.619770050048828, "min": -0.6560804843902588, "max": 96.6576156616211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06766250576142088, "min": 0.06425569807804771, "max": 0.07303508436987835, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9472750806598923, "min": 0.5112455905891484, "max": 1.0724470650539824, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013437537231809637, "min": 0.0006764906290894242, "max": 0.016652978065567803, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1881255212453349, "min": 0.006764906290894242, "max": 0.23314169291794926, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.717704570321429e-06, "min": 7.717704570321429e-06, "max": 0.0002952380587301714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001080478639845, "min": 0.0001080478639845, "max": 0.0036331483889505997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257253571428573, "min": 0.10257253571428573, "max": 0.1984126857142857, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360155000000003, "min": 1.3888888, "max": 2.6110493999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026699631785714287, "min": 0.00026699631785714287, "max": 0.009841427302857142, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00373794845, "min": 0.00373794845, "max": 0.12112383506, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010315725579857826, "min": 0.010315725579857826, "max": 0.33763137459754944, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14442016184329987, "min": 0.14442016184329987, "max": 2.363419532775879, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 303.95652173913044, "min": 271.19642857142856, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27964.0, "min": 16631.0, "max": 32362.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.672097806616322, "min": -0.999962551984936, "max": 1.7125369223119977, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 153.8329982087016, "min": -31.998801663517952, "max": 190.09159837663174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.672097806616322, "min": -0.999962551984936, "max": 1.7125369223119977, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 153.8329982087016, "min": -31.998801663517952, "max": 190.09159837663174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0331962656010823, "min": 0.029869579638224432, "max": 5.671021948404172, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0540564352995716, "min": 3.0540564352995716, "max": 96.40737312287092, "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": "1722438107", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722440470" }, "total": 2363.5148893160003, "count": 1, "self": 1.0514752250001038, "children": { "run_training.setup": { "total": 0.057399679000127435, "count": 1, "self": 0.057399679000127435 }, "TrainerController.start_learning": { "total": 2362.4060144120003, "count": 1, "self": 1.6125900189854292, "children": { "TrainerController._reset_env": { "total": 2.098628501000121, "count": 1, "self": 2.098628501000121 }, "TrainerController.advance": { "total": 2358.5606742630143, "count": 64152, "self": 1.6724070449517967, "children": { "env_step": { "total": 1705.5111777050097, "count": 64152, "self": 1557.6969978410775, "children": { "SubprocessEnvManager._take_step": { "total": 146.83804397998188, "count": 64152, "self": 5.139947631016867, "children": { "TorchPolicy.evaluate": { "total": 141.698096348965, "count": 62567, "self": 141.698096348965 } } }, "workers": { "total": 0.9761358839502918, "count": 64152, "self": 0.0, "children": { "worker_root": { "total": 2356.5761801029666, "count": 64152, "is_parallel": true, "self": 932.6853100489905, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021432590001495555, "count": 1, "is_parallel": true, "self": 0.0006917600005635904, "children": { "_process_rank_one_or_two_observation": { "total": 0.001451498999585965, "count": 8, "is_parallel": true, "self": 0.001451498999585965 } } }, "UnityEnvironment.step": { "total": 0.04820110700006808, "count": 1, "is_parallel": true, "self": 0.000906657000314226, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004659220001030917, "count": 1, "is_parallel": true, "self": 0.0004659220001030917 }, "communicator.exchange": { "total": 0.045204555999816876, "count": 1, "is_parallel": true, "self": 0.045204555999816876 }, "steps_from_proto": { "total": 0.0016239719998338842, "count": 1, "is_parallel": true, "self": 0.00033371399945281155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012902580003810726, "count": 8, "is_parallel": true, "self": 0.0012902580003810726 } } } } } } }, "UnityEnvironment.step": { "total": 1423.8908700539762, "count": 64151, "is_parallel": true, "self": 36.27989422490373, "children": { "UnityEnvironment._generate_step_input": { "total": 24.703800453022495, "count": 64151, "is_parallel": true, "self": 24.703800453022495 }, "communicator.exchange": { "total": 1258.1716859759997, "count": 64151, "is_parallel": true, "self": 1258.1716859759997 }, "steps_from_proto": { "total": 104.73548940005026, "count": 64151, "is_parallel": true, "self": 22.199431229855236, "children": { "_process_rank_one_or_two_observation": { "total": 82.53605817019502, "count": 513208, "is_parallel": true, "self": 82.53605817019502 } } } } } } } } } } }, "trainer_advance": { "total": 651.3770895130526, "count": 64152, "self": 3.319137224077622, "children": { "process_trajectory": { "total": 137.5267060869769, "count": 64152, "self": 137.286049094977, "children": { "RLTrainer._checkpoint": { "total": 0.24065699199991286, "count": 2, "self": 0.24065699199991286 } } }, "_update_policy": { "total": 510.5312462019981, "count": 456, "self": 302.4665184069854, "children": { "TorchPPOOptimizer.update": { "total": 208.0647277950127, "count": 22785, "self": 208.0647277950127 } } } } } } }, "trainer_threads": { "total": 1.5860000530665275e-06, "count": 1, "self": 1.5860000530665275e-06 }, "TrainerController._save_models": { "total": 0.13412004300016633, "count": 1, "self": 0.0021230100001048413, "children": { "RLTrainer._checkpoint": { "total": 0.1319970330000615, "count": 1, "self": 0.1319970330000615 } } } } } } }