{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6354275345802307, "min": 0.5971466302871704, "max": 1.3839876651763916, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 19093.326171875, "min": 18124.59375, "max": 41984.6484375, "count": 30 }, "Pyramids.Step.mean": { "value": 899921.0, "min": 29952.0, "max": 899921.0, "count": 30 }, "Pyramids.Step.sum": { "value": 899921.0, "min": 29952.0, "max": 899921.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.22095441818237305, "min": -0.10350140929222107, "max": 0.2463419884443283, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 56.78528594970703, "min": -24.94384002685547, "max": 62.8137321472168, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1371481567621231, "min": 0.0005479914252646267, "max": 0.6589561700820923, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 35.24707794189453, "min": 0.1408337950706482, "max": 156.172607421875, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06873789694182289, "min": 0.06555888716728968, "max": 0.07390883916412436, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0310684541273434, "min": 0.511176520427147, "max": 1.0786668786495996, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012460839376566866, "min": 0.0007991449787323235, "max": 0.017638873840436185, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.186912590648503, "min": 0.011188029702252529, "max": 0.194981423036855, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.088631637155554e-06, "min": 5.088631637155554e-06, "max": 0.000294611811319873, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.632947455733331e-05, "min": 7.632947455733331e-05, "max": 0.003448688483770555, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10169617777777777, "min": 0.10169617777777777, "max": 0.1982039365079365, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5254426666666665, "min": 1.3874275555555555, "max": 2.5434311111111114, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.00017944815999999998, "min": 0.00017944815999999998, "max": 0.00982057325714286, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.0026917224, "min": 0.0026917224, "max": 0.1149713215, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015529944561421871, "min": 0.015529944561421871, "max": 0.7040737867355347, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2329491674900055, "min": 0.23185282945632935, "max": 4.928516387939453, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 583.2448979591836, "min": 583.2448979591836, "max": 999.0, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28579.0, "min": 15984.0, "max": 32670.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8451673152799509, "min": -1.0000000521540642, "max": 1.0113673100666123, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 41.413198448717594, "min": -29.36480164527893, "max": 49.55699819326401, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8451673152799509, "min": -1.0000000521540642, "max": 1.0113673100666123, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 41.413198448717594, "min": -29.36480164527893, "max": 49.55699819326401, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09311438402771588, "min": 0.09311438402771588, "max": 14.332283766940236, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 4.562604817358078, "min": 4.562604817358078, "max": 229.31654027104378, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1775567616", "python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [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": "1.2.0.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": "1775569902" }, "total": 2286.0482561339995, "count": 1, "self": 0.5084456739991765, "children": { "run_training.setup": { "total": 0.025575739000032627, "count": 1, "self": 0.025575739000032627 }, "TrainerController.start_learning": { "total": 2285.5142347210003, "count": 1, "self": 1.698676372097907, "children": { "TrainerController._reset_env": { "total": 3.4833422409997183, "count": 1, "self": 3.4833422409997183 }, "TrainerController.advance": { "total": 2280.2441757099027, "count": 57032, "self": 1.777934987846038, "children": { "env_step": { "total": 1593.8327968219846, "count": 57032, "self": 1421.7032017390497, "children": { "SubprocessEnvManager._take_step": { "total": 171.0975039619907, "count": 57032, "self": 5.26617365016682, "children": { "TorchPolicy.evaluate": { "total": 165.83133031182388, "count": 56320, "self": 165.83133031182388 } } }, "workers": { "total": 1.0320911209441874, "count": 57032, "self": 0.0, "children": { "worker_root": { "total": 2279.6254933599375, "count": 57032, "is_parallel": true, "self": 990.1423941668304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004849366000144073, "count": 1, "is_parallel": true, "self": 0.0034124020003218902, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014369639998221828, "count": 8, "is_parallel": true, "self": 0.0014369639998221828 } } }, "UnityEnvironment.step": { "total": 0.05945651399997587, "count": 1, "is_parallel": true, "self": 0.0006613830000787857, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005815019999317883, "count": 1, "is_parallel": true, "self": 0.0005815019999317883 }, "communicator.exchange": { "total": 0.05625031099998523, "count": 1, "is_parallel": true, "self": 0.05625031099998523 }, "steps_from_proto": { "total": 0.001963317999980063, "count": 1, "is_parallel": true, "self": 0.00043131800021001254, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015319999997700506, "count": 8, "is_parallel": true, "self": 0.0015319999997700506 } } } } } } }, "UnityEnvironment.step": { "total": 1289.4830991931071, "count": 57031, "is_parallel": true, "self": 36.28539950998311, "children": { "UnityEnvironment._generate_step_input": { "total": 25.431543385100667, "count": 57031, "is_parallel": true, "self": 25.431543385100667 }, "communicator.exchange": { "total": 1104.79499485, "count": 57031, "is_parallel": true, "self": 1104.79499485 }, "steps_from_proto": { "total": 122.9711614480234, "count": 57031, "is_parallel": true, "self": 25.20556019886999, "children": { "_process_rank_one_or_two_observation": { "total": 97.7656012491534, "count": 456248, "is_parallel": true, "self": 97.7656012491534 } } } } } } } } } } }, "trainer_advance": { "total": 684.633443900072, "count": 57032, "self": 3.028081452108836, "children": { "process_trajectory": { "total": 131.00724460596484, "count": 57032, "self": 130.84091225396514, "children": { "RLTrainer._checkpoint": { "total": 0.1663323519996993, "count": 1, "self": 0.1663323519996993 } } }, "_update_policy": { "total": 550.5981178419984, "count": 405, "self": 306.13139845599926, "children": { "TorchPPOOptimizer.update": { "total": 244.4667193859991, "count": 20541, "self": 244.4667193859991 } } } } } } }, "trainer_threads": { "total": 1.0969997674692422e-06, "count": 1, "self": 1.0969997674692422e-06 }, "TrainerController._save_models": { "total": 0.08803930100020807, "count": 1, "self": 0.0011036699997930555, "children": { "RLTrainer._checkpoint": { "total": 0.08693563100041501, "count": 1, "self": 0.08693563100041501 } } } } } } }