{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6290369629859924, "min": 0.621737539768219, "max": 1.3901978731155396, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18810.720703125, "min": 18810.720703125, "max": 42173.04296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989929.0, "min": 29952.0, "max": 989929.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4591010510921478, "min": -0.09893477708101273, "max": 0.4621284008026123, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.49818420410156, "min": -23.843280792236328, "max": 123.49818420410156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.841028094291687, "min": -1.841028094291687, "max": 0.33809614181518555, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -495.2365417480469, "min": -495.2365417480469, "max": 84.59730529785156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06843858313615009, "min": 0.0649911779101995, "max": 0.0739338430362843, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9581401639061012, "min": 0.4903815134255157, "max": 1.0688281304764509, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.585869906576486, "min": 0.00035660208253024617, "max": 0.585869906576486, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 8.202178692070804, "min": 0.004992429155423446, "max": 8.202178692070804, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.491911788442857e-06, "min": 7.491911788442857e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001048867650382, "min": 0.0001048867650382, "max": 0.0036323527892158, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249727142857144, "min": 0.10249727142857144, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349618000000002, "min": 1.3886848, "max": 2.6107841999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025947741571428573, "min": 0.00025947741571428573, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00363268382, "min": 0.00363268382, "max": 0.12109734158000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012235567905008793, "min": 0.012235567905008793, "max": 0.4845544695854187, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17129795253276825, "min": 0.17129795253276825, "max": 3.391881227493286, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 413.4166666666667, "min": 377.14666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29766.0, "min": 15984.0, "max": 32981.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4754499809609518, "min": -1.0000000521540642, "max": 1.5433864635792938, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 106.23239862918854, "min": -30.322001665830612, "max": 114.21059830486774, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4754499809609518, "min": -1.0000000521540642, "max": 1.5433864635792938, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 106.23239862918854, "min": -30.322001665830612, "max": 114.21059830486774, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054591208205642436, "min": 0.05026456545906635, "max": 9.344176849350333, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9305669908062555, "min": 3.71957784397091, "max": 149.50682958960533, "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": "1762715796", "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": "1762718139" }, "total": 2342.9301643100002, "count": 1, "self": 0.4908150209998894, "children": { "run_training.setup": { "total": 0.02452640399997108, "count": 1, "self": 0.02452640399997108 }, "TrainerController.start_learning": { "total": 2342.4148228850004, "count": 1, "self": 1.6910421570773906, "children": { "TrainerController._reset_env": { "total": 2.234458074000031, "count": 1, "self": 2.234458074000031 }, "TrainerController.advance": { "total": 2338.408741410924, "count": 63576, "self": 1.760677389083412, "children": { "env_step": { "total": 1642.6637495438636, "count": 63576, "self": 1470.7910729829646, "children": { "SubprocessEnvManager._take_step": { "total": 170.8450340899326, "count": 63576, "self": 5.149912647905239, "children": { "TorchPolicy.evaluate": { "total": 165.69512144202736, "count": 62546, "self": 165.69512144202736 } } }, "workers": { "total": 1.0276424709663843, "count": 63576, "self": 0.0, "children": { "worker_root": { "total": 2335.8523926507983, "count": 63576, "is_parallel": true, "self": 996.9297211427556, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018792519999806245, "count": 1, "is_parallel": true, "self": 0.0006080140001358814, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012712379998447432, "count": 8, "is_parallel": true, "self": 0.0012712379998447432 } } }, "UnityEnvironment.step": { "total": 0.05021674299996448, "count": 1, "is_parallel": true, "self": 0.0005843449998792494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004509670002335042, "count": 1, "is_parallel": true, "self": 0.0004509670002335042 }, "communicator.exchange": { "total": 0.04732312199985245, "count": 1, "is_parallel": true, "self": 0.04732312199985245 }, "steps_from_proto": { "total": 0.0018583089999992808, "count": 1, "is_parallel": true, "self": 0.0003968369996982801, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014614720003010007, "count": 8, "is_parallel": true, "self": 0.0014614720003010007 } } } } } } }, "UnityEnvironment.step": { "total": 1338.9226715080426, "count": 63575, "is_parallel": true, "self": 35.60919586616137, "children": { "UnityEnvironment._generate_step_input": { "total": 23.85059780784013, "count": 63575, "is_parallel": true, "self": 23.85059780784013 }, "communicator.exchange": { "total": 1166.6234329560284, "count": 63575, "is_parallel": true, "self": 1166.6234329560284 }, "steps_from_proto": { "total": 112.83944487801273, "count": 63575, "is_parallel": true, "self": 24.639582878130568, "children": { "_process_rank_one_or_two_observation": { "total": 88.19986199988216, "count": 508600, "is_parallel": true, "self": 88.19986199988216 } } } } } } } } } } }, "trainer_advance": { "total": 693.984314477977, "count": 63576, "self": 3.3770003130885016, "children": { "process_trajectory": { "total": 129.323499949885, "count": 63576, "self": 129.14093984288547, "children": { "RLTrainer._checkpoint": { "total": 0.1825601069995173, "count": 2, "self": 0.1825601069995173 } } }, "_update_policy": { "total": 561.2838142150035, "count": 452, "self": 312.2106390149056, "children": { "TorchPPOOptimizer.update": { "total": 249.07317520009792, "count": 22800, "self": 249.07317520009792 } } } } } } }, "trainer_threads": { "total": 8.819997674436308e-07, "count": 1, "self": 8.819997674436308e-07 }, "TrainerController._save_models": { "total": 0.08058036099919264, "count": 1, "self": 0.001090017998649273, "children": { "RLTrainer._checkpoint": { "total": 0.07949034300054336, "count": 1, "self": 0.07949034300054336 } } } } } } }