{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2941546142101288, "min": 0.2941546142101288, "max": 1.230045199394226, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8824.638671875, "min": 8824.638671875, "max": 37314.65234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5899111032485962, "min": -0.09332969039678574, "max": 0.5899111032485962, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 304.3941345214844, "min": -44.98490905761719, "max": 304.3941345214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.012126754969358444, "min": -0.0007601370452903211, "max": 0.4414452016353607, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.257405757904053, "min": -0.38006851077079773, "max": 209.24502563476562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06886016810183516, "min": 0.06440169352960462, "max": 0.07242890500665887, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0329025215275274, "min": 0.6493727635058191, "max": 1.0717132783514292, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014852273857427966, "min": 0.0004763886122897717, "max": 0.01613930310884912, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2227841078614195, "min": 0.006669440572056803, "max": 0.2280470366337492, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5303774899066665e-06, "min": 7.5303774899066665e-06, "max": 0.0002954432015189333, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001129556623486, "min": 0.0001129556623486, "max": 0.0038923628025457997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251009333333334, "min": 0.10251009333333334, "max": 0.19848106666666668, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376514000000001, "min": 1.4773623, "max": 2.7974542000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607583240000001, "min": 0.0002607583240000001, "max": 0.00984825856, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003911374860000001, "min": 0.003911374860000001, "max": 0.12976567457999996, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01069762371480465, "min": 0.01069762371480465, "max": 0.580093502998352, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1604643613100052, "min": 0.15776585042476654, "max": 5.220841407775879, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 309.50515463917526, "min": 287.55238095238093, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30022.0, "min": 15984.0, "max": 33300.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.628614423854142, "min": -1.0000000447034836, "max": 1.6546282932724592, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 157.97559911385179, "min": -28.456401482224464, "max": 175.39059908688068, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.628614423854142, "min": -1.0000000447034836, "max": 1.6546282932724592, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 157.97559911385179, "min": -28.456401482224464, "max": 175.39059908688068, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.033848224690147394, "min": 0.033848224690147394, "max": 10.325628221035004, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.283277794944297, "min": 3.283277794944297, "max": 165.21005153656006, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1781938985", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "1781941602" }, "total": 2617.671402295, "count": 1, "self": 0.5282291039998199, "children": { "run_training.setup": { "total": 0.025092376999964472, "count": 1, "self": 0.025092376999964472 }, "TrainerController.start_learning": { "total": 2617.118080814, "count": 1, "self": 1.574541657032114, "children": { "TrainerController._reset_env": { "total": 2.2252541009997913, "count": 1, "self": 2.2252541009997913 }, "TrainerController.advance": { "total": 2613.1883443329684, "count": 63904, "self": 1.5645067239147465, "children": { "env_step": { "total": 1876.9295265180222, "count": 63904, "self": 1710.4152021159575, "children": { "SubprocessEnvManager._take_step": { "total": 165.61808246304963, "count": 63904, "self": 5.138124988961408, "children": { "TorchPolicy.evaluate": { "total": 160.47995747408822, "count": 62529, "self": 160.47995747408822 } } }, "workers": { "total": 0.8962419390149989, "count": 63904, "self": 0.0, "children": { "worker_root": { "total": 2611.3913237810707, "count": 63904, "is_parallel": true, "self": 1027.221884895068, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030878600000505685, "count": 1, "is_parallel": true, "self": 0.0010102050000568852, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020776549999936833, "count": 8, "is_parallel": true, "self": 0.0020776549999936833 } } }, "UnityEnvironment.step": { "total": 0.05208609100009198, "count": 1, "is_parallel": true, "self": 0.0006040160001248296, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004636400003619201, "count": 1, "is_parallel": true, "self": 0.0004636400003619201 }, "communicator.exchange": { "total": 0.04916409099996599, "count": 1, "is_parallel": true, "self": 0.04916409099996599 }, "steps_from_proto": { "total": 0.0018543439996392408, "count": 1, "is_parallel": true, "self": 0.0004005289993074257, "children": { "_process_rank_one_or_two_observation": { "total": 0.001453815000331815, "count": 8, "is_parallel": true, "self": 0.001453815000331815 } } } } } } }, "UnityEnvironment.step": { "total": 1584.1694388860028, "count": 63903, "is_parallel": true, "self": 35.83485496295134, "children": { "UnityEnvironment._generate_step_input": { "total": 25.281308221006384, "count": 63903, "is_parallel": true, "self": 25.281308221006384 }, "communicator.exchange": { "total": 1406.9194388799656, "count": 63903, "is_parallel": true, "self": 1406.9194388799656 }, "steps_from_proto": { "total": 116.1338368220795, "count": 63903, "is_parallel": true, "self": 23.839415339201878, "children": { "_process_rank_one_or_two_observation": { "total": 92.29442148287762, "count": 511224, "is_parallel": true, "self": 92.29442148287762 } } } } } } } } } } }, "trainer_advance": { "total": 734.6943110910315, "count": 63904, "self": 2.587938909936838, "children": { "process_trajectory": { "total": 159.1980520620832, "count": 63904, "self": 158.9085929700832, "children": { "RLTrainer._checkpoint": { "total": 0.2894590920000155, "count": 2, "self": 0.2894590920000155 } } }, "_update_policy": { "total": 572.9083201190115, "count": 469, "self": 293.0833165089325, "children": { "TorchPPOOptimizer.update": { "total": 279.82500361007897, "count": 22977, "self": 279.82500361007897 } } } } } } }, "trainer_threads": { "total": 1.2299997251830064e-06, "count": 1, "self": 1.2299997251830064e-06 }, "TrainerController._save_models": { "total": 0.12993949300016538, "count": 1, "self": 0.001520525000159978, "children": { "RLTrainer._checkpoint": { "total": 0.1284189680000054, "count": 1, "self": 0.1284189680000054 } } } } } } }