{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.26293444633483887, "min": 0.26042643189430237, "max": 1.4866414070129395, "count": 60 }, "Pyramids.Policy.Entropy.sum": { "value": 7892.24072265625, "min": 7837.7939453125, "max": 45098.75390625, "count": 60 }, "Pyramids.Step.mean": { "value": 1799975.0, "min": 29952.0, "max": 1799975.0, "count": 60 }, "Pyramids.Step.sum": { "value": 1799975.0, "min": 29952.0, "max": 1799975.0, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 1.0973327159881592, "min": -0.20249563455581665, "max": 1.1482276916503906, "count": 60 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 328.10247802734375, "min": -49.003944396972656, "max": 345.53167724609375, "count": 60 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0021718190982937813, "min": -0.03265313059091568, "max": 0.4280116856098175, "count": 60 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6493738889694214, "min": -9.175529479980469, "max": 101.43876647949219, "count": 60 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850040492815121, "min": 0.06414754834837745, "max": 0.0743288390901095, "count": 60 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0275060739222681, "min": 0.4702637614762603, "max": 1.090550015719297, "count": 60 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.009532641577405028, "min": 0.0005468851043433879, "max": 0.014255758067260363, "count": 60 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14298962366107543, "min": 0.004375080834747103, "max": 0.19958061294164509, "count": 60 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.497965834044445e-06, "min": 2.497965834044445e-06, "max": 0.00029730590565993657, "count": 60 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.746948751066668e-05, "min": 3.746948751066668e-05, "max": 0.0037458834847055545, "count": 60 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10083262222222224, "min": 0.10083262222222224, "max": 0.19910196825396828, "count": 60 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5124893333333336, "min": 1.382840888888889, "max": 2.6877068888888895, "count": 60 }, "Pyramids.Policy.Beta.mean": { "value": 9.317896000000003e-05, "min": 9.317896000000003e-05, "max": 0.00991028662857143, "count": 60 }, "Pyramids.Policy.Beta.sum": { "value": 0.0013976844000000005, "min": 0.0013976844000000005, "max": 0.124877915, "count": 60 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006006770301610231, "min": 0.006006770301610231, "max": 0.26087579131126404, "count": 60 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09010155498981476, "min": 0.08769560605287552, "max": 1.8261306285858154, "count": 60 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.900826446281, "min": 220.84848484848484, "max": 999.0, "count": 60 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30238.0, "min": 15984.0, "max": 33253.0, "count": 60 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.733568579820562, "min": -1.0000000521540642, "max": 1.7752440758342818, "count": 60 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 209.761798158288, "min": -32.000001668930054, "max": 235.56879794597626, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.733568579820562, "min": -1.0000000521540642, "max": 1.7752440758342818, "count": 60 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 209.761798158288, "min": -32.000001668930054, "max": 235.56879794597626, "count": 60 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015753499560943497, "min": 0.014964803705779343, "max": 6.419918207451701, "count": 60 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9061734468741633, "min": 1.9005300706339767, "max": 102.71869131922722, "count": 60 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 60 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1770205878", "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 --force", "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": "1770210192" }, "total": 4314.011608926, "count": 1, "self": 0.48385204700025497, "children": { "run_training.setup": { "total": 0.038731783000002906, "count": 1, "self": 0.038731783000002906 }, "TrainerController.start_learning": { "total": 4313.489025096, "count": 1, "self": 2.459269987940388, "children": { "TrainerController._reset_env": { "total": 2.3317445140000927, "count": 1, "self": 2.3317445140000927 }, "TrainerController.advance": { "total": 4308.61779794806, "count": 116416, "self": 2.6237611279930206, "children": { "env_step": { "total": 3095.3342452640477, "count": 116416, "self": 2822.3064057461743, "children": { "SubprocessEnvManager._take_step": { "total": 271.5851753839902, "count": 116416, "self": 8.398219723984766, "children": { "TorchPolicy.evaluate": { "total": 263.1869556600054, "count": 112556, "self": 263.1869556600054 } } }, "workers": { "total": 1.4426641338829995, "count": 116416, "self": 0.0, "children": { "worker_root": { "total": 4301.90529075804, "count": 116416, "is_parallel": true, "self": 1694.805922851031, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001868436999984624, "count": 1, "is_parallel": true, "self": 0.0005665720000251895, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013018649999594345, "count": 8, "is_parallel": true, "self": 0.0013018649999594345 } } }, "UnityEnvironment.step": { "total": 0.05384379799988892, "count": 1, "is_parallel": true, "self": 0.0006222719998731918, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004968010000538925, "count": 1, "is_parallel": true, "self": 0.0004968010000538925 }, "communicator.exchange": { "total": 0.05086125100001482, "count": 1, "is_parallel": true, "self": 0.05086125100001482 }, "steps_from_proto": { "total": 0.0018634739999470185, "count": 1, "is_parallel": true, "self": 0.000407303999963915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014561699999831035, "count": 8, "is_parallel": true, "self": 0.0014561699999831035 } } } } } } }, "UnityEnvironment.step": { "total": 2607.099367907009, "count": 116415, "is_parallel": true, "self": 62.94843898007275, "children": { "UnityEnvironment._generate_step_input": { "total": 43.91254910797852, "count": 116415, "is_parallel": true, "self": 43.91254910797852 }, "communicator.exchange": { "total": 2298.0207198699627, "count": 116415, "is_parallel": true, "self": 2298.0207198699627 }, "steps_from_proto": { "total": 202.21765994899488, "count": 116415, "is_parallel": true, "self": 41.543236522095185, "children": { "_process_rank_one_or_two_observation": { "total": 160.6744234268997, "count": 931320, "is_parallel": true, "self": 160.6744234268997 } } } } } } } } } } }, "trainer_advance": { "total": 1210.6597915560194, "count": 116416, "self": 4.733662971965714, "children": { "process_trajectory": { "total": 238.15320808405954, "count": 116416, "self": 237.87366150606, "children": { "RLTrainer._checkpoint": { "total": 0.27954657799955385, "count": 3, "self": 0.27954657799955385 } } }, "_update_policy": { "total": 967.7729204999941, "count": 821, "self": 535.45314591697, "children": { "TorchPPOOptimizer.update": { "total": 432.3197745830241, "count": 41079, "self": 432.3197745830241 } } } } } } }, "trainer_threads": { "total": 8.779998097452335e-07, "count": 1, "self": 8.779998097452335e-07 }, "TrainerController._save_models": { "total": 0.08021176799957175, "count": 1, "self": 0.0011216859993510297, "children": { "RLTrainer._checkpoint": { "total": 0.07909008200022072, "count": 1, "self": 0.07909008200022072 } } } } } } }