{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.091654658317566, "min": 0.9384645819664001, "max": 1.5375922918319702, "count": 17 }, "Pyramids.Policy.Entropy.sum": { "value": 32505.107421875, "min": 28108.890625, "max": 46644.3984375, "count": 17 }, "Pyramids.Step.mean": { "value": 509993.0, "min": 29952.0, "max": 509993.0, "count": 17 }, "Pyramids.Step.sum": { "value": 509993.0, "min": 29952.0, "max": 509993.0, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05219930410385132, "min": -0.1252424418926239, "max": 0.05219930410385132, "count": 17 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 12.788829803466797, "min": -30.183429718017578, "max": 12.788829803466797, "count": 17 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0006059624720364809, "min": -0.0006059624720364809, "max": 0.12357236444950104, "count": 17 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.14846080541610718, "min": -0.14846080541610718, "max": 29.657367706298828, "count": 17 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07170131279138328, "min": 0.06666870358060957, "max": 0.07256212287585669, "count": 17 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.003818379079366, "min": 0.486426788872983, "max": 1.0158697202619935, "count": 17 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.003950200436650318, "min": 0.00019073321958985648, "max": 0.003950200436650318, "count": 17 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.05530280611310445, "min": 0.0013351325371289953, "max": 0.05530280611310445, "count": 17 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002505246307775095, "min": 0.0002505246307775095, "max": 0.00029838354339596195, "count": 17 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0035073448308851327, "min": 0.002027104024298666, "max": 0.003759117846960767, "count": 17 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.18350820476190477, "min": 0.18350820476190477, "max": 0.19946118095238097, "count": 17 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.5691148666666668, "min": 1.3757013333333334, "max": 2.6530392333333337, "count": 17 }, "Pyramids.Policy.Beta.mean": { "value": 0.008352469655714286, "min": 0.008352469655714286, "max": 0.009946171977142856, "count": 17 }, "Pyramids.Policy.Beta.sum": { "value": 0.11693457518, "min": 0.06757256319999999, "max": 0.12531861941, "count": 17 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012286539189517498, "min": 0.012286539189517498, "max": 0.25565576553344727, "count": 17 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17201155424118042, "min": 0.17201155424118042, "max": 1.7895903587341309, "count": 17 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 784.8181818181819, "min": 784.8181818181819, "max": 999.0, "count": 17 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 25899.0, "min": 15984.0, "max": 32802.0, "count": 17 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.07101207813530257, "min": -1.0000000521540642, "max": 0.07101207813530257, "count": 17 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 2.343398578464985, "min": -32.000001668930054, "max": 2.343398578464985, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.07101207813530257, "min": -1.0000000521540642, "max": 0.07101207813530257, "count": 17 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 2.343398578464985, "min": -32.000001668930054, "max": 2.343398578464985, "count": 17 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10121015209535306, "min": 0.10121015209535306, "max": 4.783630364574492, "count": 17 }, "Pyramids.Policy.RndReward.sum": { "value": 3.339935019146651, "min": 3.339935019146651, "max": 76.53808583319187, "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": "1750163079", "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": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1750164111" }, "total": 1032.544884088, "count": 1, "self": 0.3442103610000231, "children": { "run_training.setup": { "total": 0.019710605000000214, "count": 1, "self": 0.019710605000000214 }, "TrainerController.start_learning": { "total": 1032.1809631219999, "count": 1, "self": 0.6586191789906479, "children": { "TrainerController._reset_env": { "total": 2.1315825730000597, "count": 1, "self": 2.1315825730000597 }, "TrainerController.advance": { "total": 1029.2581475590093, "count": 33813, "self": 0.7048291439925833, "children": { "env_step": { "total": 688.1020870330017, "count": 33813, "self": 610.5431492730163, "children": { "SubprocessEnvManager._take_step": { "total": 77.14016001398079, "count": 33813, "self": 2.411945329995774, "children": { "TorchPolicy.evaluate": { "total": 74.72821468398502, "count": 33610, "self": 74.72821468398502 } } }, "workers": { "total": 0.4187777460045936, "count": 33812, "self": 0.0, "children": { "worker_root": { "total": 1029.5994874460152, "count": 33812, "is_parallel": true, "self": 476.03400405898583, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019370009999875037, "count": 1, "is_parallel": true, "self": 0.0006673279999631632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012696730000243406, "count": 8, "is_parallel": true, "self": 0.0012696730000243406 } } }, "UnityEnvironment.step": { "total": 0.04849237400003403, "count": 1, "is_parallel": true, "self": 0.0005276570000205538, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004676359999393753, "count": 1, "is_parallel": true, "self": 0.0004676359999393753 }, "communicator.exchange": { "total": 0.045872199000086766, "count": 1, "is_parallel": true, "self": 0.045872199000086766 }, "steps_from_proto": { "total": 0.0016248819999873376, "count": 1, "is_parallel": true, "self": 0.0003557599995929195, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012691220003944181, "count": 8, "is_parallel": true, "self": 0.0012691220003944181 } } } } } } }, "UnityEnvironment.step": { "total": 553.5654833870294, "count": 33811, "is_parallel": true, "self": 16.459230925053703, "children": { "UnityEnvironment._generate_step_input": { "total": 11.797558100995616, "count": 33811, "is_parallel": true, "self": 11.797558100995616 }, "communicator.exchange": { "total": 475.7390978319777, "count": 33811, "is_parallel": true, "self": 475.7390978319777 }, "steps_from_proto": { "total": 49.56959652900241, "count": 33811, "is_parallel": true, "self": 9.79340230600701, "children": { "_process_rank_one_or_two_observation": { "total": 39.7761942229954, "count": 270488, "is_parallel": true, "self": 39.7761942229954 } } } } } } } } } } }, "trainer_advance": { "total": 340.45123138201495, "count": 33812, "self": 1.1056509010139735, "children": { "process_trajectory": { "total": 63.49504269199929, "count": 33812, "self": 63.39192717399942, "children": { "RLTrainer._checkpoint": { "total": 0.10311551799986773, "count": 1, "self": 0.10311551799986773 } } }, "_update_policy": { "total": 275.8505377890017, "count": 209, "self": 155.1174084920001, "children": { "TorchPPOOptimizer.update": { "total": 120.7331292970016, "count": 12330, "self": 120.7331292970016 } } } } } } }, "trainer_threads": { "total": 1.1979998362221522e-06, "count": 1, "self": 1.1979998362221522e-06 }, "TrainerController._save_models": { "total": 0.13261261299999205, "count": 1, "self": 0.0015488270000787452, "children": { "RLTrainer._checkpoint": { "total": 0.1310637859999133, "count": 1, "self": 0.1310637859999133 } } } } } } }