{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.0858614444732666, "min": 1.076594591140747, "max": 1.6008358001708984, "count": 12 }, "Pyramids.Policy.Entropy.sum": { "value": 5559.6103515625, "min": 5098.751953125, "max": 8196.279296875, "count": 12 }, "Pyramids.Step.mean": { "value": 59968.0, "min": 4992.0, "max": 59968.0, "count": 12 }, "Pyramids.Step.sum": { "value": 59968.0, "min": 4992.0, "max": 59968.0, "count": 12 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09700147807598114, "min": -0.09802542626857758, "max": 0.03143466264009476, "count": 12 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -7.566115379333496, "min": -7.717857360839844, "max": 2.451903820037842, "count": 12 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4251978099346161, "min": 0.4251978099346161, "max": 1.6430084705352783, "count": 12 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 33.165428161621094, "min": 33.165428161621094, "max": 128.1546630859375, "count": 12 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.1043597343887086, "min": 0.0908307566295172, "max": 0.10888732827879721, "count": 12 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.2087194687774172, "min": 0.1816615132590344, "max": 0.31693804504175205, "count": 12 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0015953237875692139, "min": 0.0015953237875692139, "max": 0.28529408150643576, "count": 12 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0031906475751384278, "min": 0.0031906475751384278, "max": 0.5705881630128715, "count": 12 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.320009536e-05, "min": 2.320009536e-05, "max": 0.00047440000511999995, "count": 12 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.640019072e-05, "min": 4.640019072e-05, "max": 0.00119280006144, "count": 12 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10464000000000001, "min": 0.10464000000000001, "max": 0.19488000000000003, "count": 12 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.20928000000000002, "min": 0.20928000000000002, "max": 0.53856, "count": 12 }, "Pyramids.Policy.Beta.mean": { "value": 0.00024153599999999999, "min": 0.00024153599999999999, "max": 0.004744511999999999, "count": 12 }, "Pyramids.Policy.Beta.sum": { "value": 0.00048307199999999997, "min": 0.00048307199999999997, "max": 0.011934144, "count": 12 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.1158340722322464, "min": 0.1158340722322464, "max": 2.0659866333007812, "count": 12 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2316681444644928, "min": 0.2316681444644928, "max": 4.1319732666015625, "count": 12 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 12 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 12 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 3 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 3 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": -1.0000000447034836, "count": 3 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000715255737, "min": -16.000000715255737, "max": -16.000000715255737, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000447034836, "min": -1.0000000447034836, "max": -1.0000000447034836, "count": 3 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000715255737, "min": -16.000000715255737, "max": -16.000000715255737, "count": 3 }, "Pyramids.Policy.RndReward.mean": { "value": 3.456511293305084, "min": 3.456511293305084, "max": 26.796036721672863, "count": 3 }, "Pyramids.Policy.RndReward.sum": { "value": 55.304180692881346, "min": 55.304180692881346, "max": 428.7365875467658, "count": 3 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1773224626", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1773224824" }, "total": 198.1202117439998, "count": 1, "self": 0.6933288059999541, "children": { "run_training.setup": { "total": 0.05198986000004879, "count": 1, "self": 0.05198986000004879 }, "TrainerController.start_learning": { "total": 197.3748930779998, "count": 1, "self": 0.16538524699490154, "children": { "TrainerController._reset_env": { "total": 5.734944684000311, "count": 1, "self": 5.734944684000311 }, "TrainerController.advance": { "total": 191.29461991900416, "count": 3768, "self": 0.1767727360279423, "children": { "env_step": { "total": 138.4266464290008, "count": 3768, "self": 126.94886692699902, "children": { "SubprocessEnvManager._take_step": { "total": 11.376938860012615, "count": 3768, "self": 0.565294633020585, "children": { "TorchPolicy.evaluate": { "total": 10.81164422699203, "count": 3768, "self": 10.81164422699203 } } }, "workers": { "total": 0.10084064198917986, "count": 3768, "self": 0.0, "children": { "worker_root": { "total": 196.26455378900891, "count": 3768, "is_parallel": true, "self": 83.58021445699251, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004079227000147512, "count": 1, "is_parallel": true, "self": 0.0014007879999553552, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026784390001921565, "count": 8, "is_parallel": true, "self": 0.0026784390001921565 } } }, "UnityEnvironment.step": { "total": 0.3154874319998271, "count": 1, "is_parallel": true, "self": 0.0008267520001936646, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000569591999919794, "count": 1, "is_parallel": true, "self": 0.000569591999919794 }, "communicator.exchange": { "total": 0.3074409939999896, "count": 1, "is_parallel": true, "self": 0.3074409939999896 }, "steps_from_proto": { "total": 0.006650093999724049, "count": 1, "is_parallel": true, "self": 0.0004911239998364181, "children": { "_process_rank_one_or_two_observation": { "total": 0.006158969999887631, "count": 8, "is_parallel": true, "self": 0.006158969999887631 } } } } } } }, "UnityEnvironment.step": { "total": 112.6843393320164, "count": 3767, "is_parallel": true, "self": 3.2743693860056737, "children": { "UnityEnvironment._generate_step_input": { "total": 2.3296677149996867, "count": 3767, "is_parallel": true, "self": 2.3296677149996867 }, "communicator.exchange": { "total": 96.15867299300362, "count": 3767, "is_parallel": true, "self": 96.15867299300362 }, "steps_from_proto": { "total": 10.921629238007426, "count": 3767, "is_parallel": true, "self": 2.311653261023366, "children": { "_process_rank_one_or_two_observation": { "total": 8.60997597698406, "count": 30136, "is_parallel": true, "self": 8.60997597698406 } } } } } } } } } } }, "trainer_advance": { "total": 52.69120075397541, "count": 3768, "self": 0.21543789197721708, "children": { "process_trajectory": { "total": 14.5903638389982, "count": 3768, "self": 14.5903638389982 }, "_update_policy": { "total": 37.88539902299999, "count": 29, "self": 18.93668053099873, "children": { "TorchPPOOptimizer.update": { "total": 18.948718492001262, "count": 1820, "self": 18.948718492001262 } } } } } } }, "trainer_threads": { "total": 1.1860001905006357e-06, "count": 1, "self": 1.1860001905006357e-06 }, "TrainerController._save_models": { "total": 0.17994204200022068, "count": 1, "self": 0.0006719660004819161, "children": { "RLTrainer._checkpoint": { "total": 0.17927007599973876, "count": 1, "self": 0.17927007599973876 } } } } } } }