{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4509788155555725, "min": 0.4509788155555725, "max": 1.4003734588623047, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13536.580078125, "min": 13444.806640625, "max": 42481.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3352579176425934, "min": -0.08843117207288742, "max": 0.4124199151992798, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 87.5023193359375, "min": -21.223482131958008, "max": 112.59063720703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.102295882999897, "min": -0.102295882999897, "max": 0.4489445090293884, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -26.69922637939453, "min": -26.69922637939453, "max": 107.7466812133789, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0693691586135627, "min": 0.06440655503355826, "max": 0.07240279649700877, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9711682205898778, "min": 0.5000358172364522, "max": 1.0682327381287264, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01904471817186338, "min": 0.0007915219617923386, "max": 0.01904471817186338, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26662605440608733, "min": 0.006332175694338709, "max": 0.26662605440608733, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.428333238207143e-06, "min": 7.428333238207143e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001039966653349, "min": 0.0001039966653349, "max": 0.0033752629749124, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247607857142858, "min": 0.10247607857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346651000000001, "min": 1.3691136000000002, "max": 2.4846914000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002573602492857143, "min": 0.0002573602492857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036030434900000004, "min": 0.0036030434900000004, "max": 0.11252625123999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01707293465733528, "min": 0.016632163897156715, "max": 0.7517451047897339, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23902109265327454, "min": 0.23285029828548431, "max": 5.262215614318848, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 463.92424242424244, "min": 425.7042253521127, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30619.0, "min": 15984.0, "max": 33875.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2731817962996888, "min": -1.0000000521540642, "max": 1.4615887097069915, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 84.02999855577946, "min": -32.000001668930054, "max": 103.7727983891964, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2731817962996888, "min": -1.0000000521540642, "max": 1.4615887097069915, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 84.02999855577946, "min": -32.000001668930054, "max": 103.7727983891964, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08077332623758014, "min": 0.07736101457160491, "max": 14.34756095521152, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.33103953168029, "min": 5.138807103605359, "max": 229.56097528338432, "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": "1781073957", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "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": "1781076502" }, "total": 2545.292901467, "count": 1, "self": 0.8441568699995514, "children": { "run_training.setup": { "total": 0.02469042500024443, "count": 1, "self": 0.02469042500024443 }, "TrainerController.start_learning": { "total": 2544.424054172, "count": 1, "self": 1.6330492698812122, "children": { "TrainerController._reset_env": { "total": 2.189360659000158, "count": 1, "self": 2.189360659000158 }, "TrainerController.advance": { "total": 2540.4677484661192, "count": 63574, "self": 1.619265965059185, "children": { "env_step": { "total": 1842.7876201809731, "count": 63574, "self": 1671.0502203580218, "children": { "SubprocessEnvManager._take_step": { "total": 170.7936539319985, "count": 63574, "self": 5.095862474003297, "children": { "TorchPolicy.evaluate": { "total": 165.6977914579952, "count": 62576, "self": 165.6977914579952 } } }, "workers": { "total": 0.9437458909528686, "count": 63574, "self": 0.0, "children": { "worker_root": { "total": 2538.45189064405, "count": 63574, "is_parallel": true, "self": 996.3487142880485, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001954257999841502, "count": 1, "is_parallel": true, "self": 0.0007278459997905884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012264120000509138, "count": 8, "is_parallel": true, "self": 0.0012264120000509138 } } }, "UnityEnvironment.step": { "total": 0.05152630299971861, "count": 1, "is_parallel": true, "self": 0.0005720809995182208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042921000022033695, "count": 1, "is_parallel": true, "self": 0.00042921000022033695 }, "communicator.exchange": { "total": 0.0487769629999093, "count": 1, "is_parallel": true, "self": 0.0487769629999093 }, "steps_from_proto": { "total": 0.0017480490000707505, "count": 1, "is_parallel": true, "self": 0.00038666300042677904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013613859996439714, "count": 8, "is_parallel": true, "self": 0.0013613859996439714 } } } } } } }, "UnityEnvironment.step": { "total": 1542.1031763560013, "count": 63573, "is_parallel": true, "self": 34.843647935070294, "children": { "UnityEnvironment._generate_step_input": { "total": 24.797576023961938, "count": 63573, "is_parallel": true, "self": 24.797576023961938 }, "communicator.exchange": { "total": 1364.9630108918768, "count": 63573, "is_parallel": true, "self": 1364.9630108918768 }, "steps_from_proto": { "total": 117.49894150509226, "count": 63573, "is_parallel": true, "self": 24.607476493179547, "children": { "_process_rank_one_or_two_observation": { "total": 92.89146501191271, "count": 508584, "is_parallel": true, "self": 92.89146501191271 } } } } } } } } } } }, "trainer_advance": { "total": 696.0608623200869, "count": 63574, "self": 3.150574159111329, "children": { "process_trajectory": { "total": 134.56850047598118, "count": 63574, "self": 134.32755888198153, "children": { "RLTrainer._checkpoint": { "total": 0.24094159399965065, "count": 2, "self": 0.24094159399965065 } } }, "_update_policy": { "total": 558.3417876849944, "count": 444, "self": 307.10422799091793, "children": { "TorchPPOOptimizer.update": { "total": 251.23755969407648, "count": 22821, "self": 251.23755969407648 } } } } } } }, "trainer_threads": { "total": 1.7060001482605003e-06, "count": 1, "self": 1.7060001482605003e-06 }, "TrainerController._save_models": { "total": 0.13389407099930395, "count": 1, "self": 0.0014610659991376451, "children": { "RLTrainer._checkpoint": { "total": 0.1324330050001663, "count": 1, "self": 0.1324330050001663 } } } } } } }