{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.120480477809906, "min": 0.11592471599578857, "max": 1.5874193906784058, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3689.59423828125, "min": 3462.609130859375, "max": 50797.421875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999929.0, "min": 29560.0, "max": 2999929.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999929.0, "min": 29560.0, "max": 2999929.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 1.0336419343948364, "min": -0.08844733983278275, "max": 1.1377360820770264, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.50802612304688, "min": -5.483735084533691, "max": 171.79815673828125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.17655682563781738, "min": 0.17141778767108917, "max": 8.814286231994629, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.658615112304688, "min": 23.658615112304688, "max": 528.857177734375, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0678099990593084, "min": 0.0652631725372136, "max": 0.07341942068417125, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9493399868303176, "min": 0.22025826205251373, "max": 1.0184781826032043, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010579818666129672, "min": 0.0075454162782335596, "max": 6.112139113759622, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1481174613258154, "min": 0.09809041161703627, "max": 18.336417341278867, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.086923485500009e-07, "min": 5.086923485500009e-07, "max": 9.946240053760001e-05, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.1216928797000135e-06, "min": 7.1216928797000135e-06, "max": 0.0012949191384143, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10025429642857142, "min": 0.10025429642857142, "max": 0.1497312, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.40356015, "min": 0.4491936, "max": 2.0474595166666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 3.537878357142863e-05, "min": 3.537878357142863e-05, "max": 0.0049731737600000004, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0004953029700000008, "min": 0.0004953029700000008, "max": 0.06475645976333333, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.029077773913741112, "min": 0.02837519161403179, "max": 2.857499837875366, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.40708884596824646, "min": 0.3890349268913269, "max": 8.57249927520752, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 233.0873015873016, "min": 202.46938775510205, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29369.0, "min": 19021.0, "max": 32365.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7503174311584897, "min": -1.0000000596046448, "max": 1.7970205235154662, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 220.5399963259697, "min": -28.000001668930054, "max": 267.3429970741272, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7503174311584897, "min": -1.0000000596046448, "max": 1.7970205235154662, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 220.5399963259697, "min": -28.000001668930054, "max": 267.3429970741272, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.3582887586265329, "min": 0.3408968039367297, "max": 247.367515846535, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 45.14438358694315, "min": 45.14438358694315, "max": 6678.922927856445, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1726639607", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726648416" }, "total": 8809.083367394001, "count": 1, "self": 0.5358093630002259, "children": { "run_training.setup": { "total": 0.0773793860000751, "count": 1, "self": 0.0773793860000751 }, "TrainerController.start_learning": { "total": 8808.470178645, "count": 1, "self": 4.131340977975924, "children": { "TrainerController._reset_env": { "total": 3.3101524130000826, "count": 1, "self": 3.3101524130000826 }, "TrainerController.advance": { "total": 8800.919145981024, "count": 196283, "self": 4.090447587641393, "children": { "env_step": { "total": 5655.40742349231, "count": 196283, "self": 5116.8528913124655, "children": { "SubprocessEnvManager._take_step": { "total": 536.0457191310076, "count": 196283, "self": 13.932800421995125, "children": { "TorchPolicy.evaluate": { "total": 522.1129187090124, "count": 187652, "self": 522.1129187090124 } } }, "workers": { "total": 2.508813048836714, "count": 196283, "self": 0.0, "children": { "worker_root": { "total": 8792.475132494816, "count": 196283, "is_parallel": true, "self": 4046.625151891779, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024285349999217942, "count": 1, "is_parallel": true, "self": 0.0006705189997546768, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017580160001671175, "count": 8, "is_parallel": true, "self": 0.0017580160001671175 } } }, "UnityEnvironment.step": { "total": 0.048741700000050514, "count": 1, "is_parallel": true, "self": 0.0007070269999758239, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044839600002433144, "count": 1, "is_parallel": true, "self": 0.00044839600002433144 }, "communicator.exchange": { "total": 0.04587008099997547, "count": 1, "is_parallel": true, "self": 0.04587008099997547 }, "steps_from_proto": { "total": 0.0017161960000748877, "count": 1, "is_parallel": true, "self": 0.0003532489999997779, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013629470000751098, "count": 8, "is_parallel": true, "self": 0.0013629470000751098 } } } } } } }, "UnityEnvironment.step": { "total": 4745.849980603037, "count": 196282, "is_parallel": true, "self": 100.62413507591828, "children": { "UnityEnvironment._generate_step_input": { "total": 68.55574473311856, "count": 196282, "is_parallel": true, "self": 68.55574473311856 }, "communicator.exchange": { "total": 4277.860185039084, "count": 196282, "is_parallel": true, "self": 4277.860185039084 }, "steps_from_proto": { "total": 298.8099157549159, "count": 196282, "is_parallel": true, "self": 61.160367077778915, "children": { "_process_rank_one_or_two_observation": { "total": 237.64954867713698, "count": 1570256, "is_parallel": true, "self": 237.64954867713698 } } } } } } } } } } }, "trainer_advance": { "total": 3141.421274901074, "count": 196283, "self": 9.627312215257007, "children": { "process_trajectory": { "total": 365.83483695880545, "count": 196283, "self": 364.8032592338052, "children": { "RLTrainer._checkpoint": { "total": 1.0315777250002611, "count": 6, "self": 1.0315777250002611 } } }, "_update_policy": { "total": 2765.9591257270113, "count": 1315, "self": 1495.0012805201413, "children": { "TorchPPOOptimizer.update": { "total": 1270.95784520687, "count": 114145, "self": 1270.95784520687 } } } } } } }, "trainer_threads": { "total": 8.8600063463673e-07, "count": 1, "self": 8.8600063463673e-07 }, "TrainerController._save_models": { "total": 0.1095383869997022, "count": 1, "self": 0.0015986430007615127, "children": { "RLTrainer._checkpoint": { "total": 0.10793974399894068, "count": 1, "self": 0.10793974399894068 } } } } } } }