{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45375317335128784, "min": 0.45375317335128784, "max": 0.4908826947212219, "count": 5 }, "Pyramids.Policy.Entropy.sum": { "value": 13779.576171875, "min": 1005.3277587890625, "max": 14382.986328125, "count": 5 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 292.47058823529414, "min": 120.0, "max": 334.6595744680851, "count": 5 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29832.0, "min": 240.0, "max": 31458.0, "count": 5 }, "Pyramids.Step.mean": { "value": 989994.0, "min": 869980.0, "max": 989994.0, "count": 5 }, "Pyramids.Step.sum": { "value": 989994.0, "min": 869980.0, "max": 989994.0, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.648196816444397, "min": 0.28400111198425293, "max": 0.648196816444397, "count": 5 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.68067932128906, "min": 3.408013343811035, "max": 186.68067932128906, "count": 5 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03853893280029297, "min": -0.03853893280029297, "max": 0.04125455394387245, "count": 5 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.099212646484375, "min": -11.099212646484375, "max": 11.592529296875, "count": 5 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6284607730659784, "min": 1.6003118093295763, "max": 1.8799999952316284, "count": 5 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.1029988527298, "min": 3.759999990463257, "max": 166.1029988527298, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6284607730659784, "min": 1.6003118093295763, "max": 1.8799999952316284, "count": 5 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.1029988527298, "min": 3.759999990463257, "max": 166.1029988527298, "count": 5 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030865185735784312, "min": 0.016379432287067175, "max": 0.03359524239297776, "count": 5 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1482489450499997, "min": 0.03275886457413435, "max": 3.1482489450499997, "count": 5 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0663118363001905, "min": 0.06482331908323215, "max": 0.07043952625697582, "count": 4 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.928365708202667, "min": 0.9075264671652501, "max": 1.0565928938546372, "count": 4 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015544505459339625, "min": 0.015379815970987285, "max": 0.016586216979443895, "count": 4 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21762307643075476, "min": 0.21618718673319867, "max": 0.23220703771221451, "count": 4 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.515933209007141e-06, "min": 7.515933209007141e-06, "max": 3.4696674148757144e-05, "count": 4 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010522306492609998, "min": 0.00010522306492609998, "max": 0.0004857534380826, "count": 4 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250527857142859, "min": 0.10250527857142859, "max": 0.11156552857142857, "count": 4 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350739000000003, "min": 1.4350739000000003, "max": 1.6275063000000003, "count": 4 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026027732928571426, "min": 0.00026027732928571426, "max": 0.0011653963042857149, "count": 4 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036438826099999995, "min": 0.0036438826099999995, "max": 0.016315548260000007, "count": 4 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01012833695858717, "min": 0.009660748764872551, "max": 0.01012833695858717, "count": 4 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14179672300815582, "min": 0.13525047898292542, "max": 0.14977973699569702, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790280270", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/lucky/mlagents-venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsL --no-graphics --resume --base-port=5305", "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": "1790280558" }, "total": 288.34727079699996, "count": 1, "self": 0.3259351539999784, "children": { "run_training.setup": { "total": 0.01804593299999624, "count": 1, "self": 0.01804593299999624 }, "TrainerController.start_learning": { "total": 288.00328971, "count": 1, "self": 0.21985994700077072, "children": { "TrainerController._reset_env": { "total": 2.765777658999994, "count": 1, "self": 2.765777658999994 }, "TrainerController.advance": { "total": 284.9849254899992, "count": 8617, "self": 0.1989222749966757, "children": { "env_step": { "total": 218.61546158400066, "count": 8617, "self": 205.51311684699874, "children": { "SubprocessEnvManager._take_step": { "total": 12.969447858000848, "count": 8617, "self": 0.5855183049991837, "children": { "TorchPolicy.evaluate": { "total": 12.383929553001664, "count": 8272, "self": 12.383929553001664 } } }, "workers": { "total": 0.1328968790010805, "count": 8617, "self": 0.0, "children": { "worker_root": { "total": 287.2903261199989, "count": 8617, "is_parallel": true, "self": 96.09303918599983, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014617100000009486, "count": 1, "is_parallel": true, "self": 0.0005265650000154665, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009351449999854822, "count": 8, "is_parallel": true, "self": 0.0009351449999854822 } } }, "UnityEnvironment.step": { "total": 0.05805246900000327, "count": 1, "is_parallel": true, "self": 0.0002394560000027468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003879759999989574, "count": 1, "is_parallel": true, "self": 0.0003879759999989574 }, "communicator.exchange": { "total": 0.056759345000003236, "count": 1, "is_parallel": true, "self": 0.056759345000003236 }, "steps_from_proto": { "total": 0.0006656919999983302, "count": 1, "is_parallel": true, "self": 0.0001539609999952063, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005117310000031239, "count": 8, "is_parallel": true, "self": 0.0005117310000031239 } } } } } } }, "UnityEnvironment.step": { "total": 191.19728693399907, "count": 8616, "is_parallel": true, "self": 2.764317716001244, "children": { "UnityEnvironment._generate_step_input": { "total": 2.7766433630010994, "count": 8616, "is_parallel": true, "self": 2.7766433630010994 }, "communicator.exchange": { "total": 177.73970503599696, "count": 8616, "is_parallel": true, "self": 177.73970503599696 }, "steps_from_proto": { "total": 7.916620818999789, "count": 8616, "is_parallel": true, "self": 2.003271342005533, "children": { "_process_rank_one_or_two_observation": { "total": 5.913349476994256, "count": 68928, "is_parallel": true, "self": 5.913349476994256 } } } } } } } } } } }, "trainer_advance": { "total": 66.17054163100187, "count": 8617, "self": 0.3731623370055104, "children": { "process_trajectory": { "total": 11.84937258399637, "count": 8617, "self": 11.752087785996395, "children": { "RLTrainer._checkpoint": { "total": 0.09728479799997558, "count": 1, "self": 0.09728479799997558 } } }, "_update_policy": { "total": 53.94800670999999, "count": 62, "self": 25.379436886998846, "children": { "TorchPPOOptimizer.update": { "total": 28.56856982300114, "count": 2976, "self": 28.56856982300114 } } } } } } }, "trainer_threads": { "total": 6.989999974393868e-07, "count": 1, "self": 6.989999974393868e-07 }, "TrainerController._save_models": { "total": 0.03272591500001454, "count": 1, "self": 0.001201431000026787, "children": { "RLTrainer._checkpoint": { "total": 0.03152448399998775, "count": 1, "self": 0.03152448399998775 } } } } } } }