{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.639274537563324, "min": 0.5915811061859131, "max": 1.4332571029663086, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 19188.46484375, "min": 17737.96875, "max": 43479.2890625, "count": 17 }, "Pyramids.Step.mean": { "value": 509935.0, "min": 29952.0, "max": 509935.0, "count": 17 }, "Pyramids.Step.sum": { "value": 509935.0, "min": 29952.0, "max": 509935.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.11859557032585144, "min": -0.10357686877250671, "max": 0.12504062056541443, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 29.411701202392578, "min": -25.065601348876953, "max": 29.634628295898438, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016931630671024323, "min": 0.016931630671024323, "max": 0.5171031951904297, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.199044227600098, "min": 4.199044227600098, "max": 122.55345916748047, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06818488614515635, "min": 0.0657610722773621, "max": 0.07274229939553108, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9545884060321888, "min": 0.4722085593240844, "max": 1.043816227892724, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010209054549653932, "min": 0.0009644156510168019, "max": 0.014433882215921292, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14292676369515506, "min": 0.006750909557117614, "max": 0.14292676369515506, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.952576007436974e-06, "min": 8.952576007436974e-06, "max": 0.0002904914317409524, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00012533606410411764, "min": 0.00012533606410411764, "max": 0.0028422628055203925, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10298415966386557, "min": 0.10298415966386557, "max": 0.1968304761904762, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.441778235294118, "min": 1.3394384313725491, "max": 2.347420784313725, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.00030811755042016805, "min": 0.00030811755042016805, "max": 0.009683364571428571, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.004313645705882353, "min": 0.004313645705882353, "max": 0.09478733635294119, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.024871045723557472, "min": 0.024871045723557472, "max": 0.642286479473114, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3481946289539337, "min": 0.3481946289539337, "max": 4.496005535125732, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 764.578947368421, "min": 734.275, "max": 999.0, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29054.0, "min": 15984.0, "max": 32542.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.4983473263288799, "min": -1.0000000521540642, "max": 0.4983473263288799, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 18.937198400497437, "min": -32.000001668930054, "max": 18.937198400497437, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.4983473263288799, "min": -1.0000000521540642, "max": 0.4983473263288799, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 18.937198400497437, "min": -32.000001668930054, "max": 18.937198400497437, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.20070622358042256, "min": 0.20070622358042256, "max": 13.79836150072515, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 7.6268364960560575, "min": 7.6268364960560575, "max": 220.7737840116024, "count": 17 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704188202", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704189301" }, "total": 1099.137461053, "count": 1, "self": 0.49136940900007176, "children": { "run_training.setup": { "total": 0.06661161799979709, "count": 1, "self": 0.06661161799979709 }, "TrainerController.start_learning": { "total": 1098.579480026, "count": 1, "self": 0.7164097740055695, "children": { "TrainerController._reset_env": { "total": 2.4781658629999583, "count": 1, "self": 2.4781658629999583 }, "TrainerController.advance": { "total": 1095.3017732739945, "count": 32245, "self": 0.7304094999669815, "children": { "env_step": { "total": 773.0819093490215, "count": 32245, "self": 702.4890763390185, "children": { "SubprocessEnvManager._take_step": { "total": 70.13889533697579, "count": 32245, "self": 2.525001555978861, "children": { "TorchPolicy.evaluate": { "total": 67.61389378099693, "count": 31935, "self": 67.61389378099693 } } }, "workers": { "total": 0.45393767302721244, "count": 32245, "self": 0.0, "children": { "worker_root": { "total": 1095.9815441419985, "count": 32245, "is_parallel": true, "self": 457.2725648129915, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026979579999988346, "count": 1, "is_parallel": true, "self": 0.0007224289997793676, "children": { "_process_rank_one_or_two_observation": { "total": 0.001975529000219467, "count": 8, "is_parallel": true, "self": 0.001975529000219467 } } }, "UnityEnvironment.step": { "total": 0.06406370099989545, "count": 1, "is_parallel": true, "self": 0.0007856179995542334, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005379640001592634, "count": 1, "is_parallel": true, "self": 0.0005379640001592634 }, "communicator.exchange": { "total": 0.06111625600010484, "count": 1, "is_parallel": true, "self": 0.06111625600010484 }, "steps_from_proto": { "total": 0.0016238630000771082, "count": 1, "is_parallel": true, "self": 0.00034962500058099977, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012742379994961084, "count": 8, "is_parallel": true, "self": 0.0012742379994961084 } } } } } } }, "UnityEnvironment.step": { "total": 638.708979329007, "count": 32244, "is_parallel": true, "self": 18.538913360987635, "children": { "UnityEnvironment._generate_step_input": { "total": 13.679534008974088, "count": 32244, "is_parallel": true, "self": 13.679534008974088 }, "communicator.exchange": { "total": 552.2876547070209, "count": 32244, "is_parallel": true, "self": 552.2876547070209 }, "steps_from_proto": { "total": 54.20287725202434, "count": 32244, "is_parallel": true, "self": 10.996816603038269, "children": { "_process_rank_one_or_two_observation": { "total": 43.20606064898607, "count": 257952, "is_parallel": true, "self": 43.20606064898607 } } } } } } } } } } }, "trainer_advance": { "total": 321.489454425006, "count": 32245, "self": 1.3052822480221948, "children": { "process_trajectory": { "total": 65.06064911698195, "count": 32245, "self": 64.95811968998169, "children": { "RLTrainer._checkpoint": { "total": 0.10252942700026324, "count": 1, "self": 0.10252942700026324 } } }, "_update_policy": { "total": 255.12352306000184, "count": 212, "self": 151.62375964099147, "children": { "TorchPPOOptimizer.update": { "total": 103.49976341901038, "count": 11664, "self": 103.49976341901038 } } } } } } }, "trainer_threads": { "total": 9.059999683813658e-07, "count": 1, "self": 9.059999683813658e-07 }, "TrainerController._save_models": { "total": 0.0831302090000463, "count": 1, "self": 0.001595688000179507, "children": { "RLTrainer._checkpoint": { "total": 0.0815345209998668, "count": 1, "self": 0.0815345209998668 } } } } } } }