{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.284467488527298, "min": 0.284467488527298, "max": 1.514824628829956, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8579.5390625, "min": 8524.552734375, "max": 45953.71875, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5809762477874756, "min": -0.1504213958978653, "max": 0.6337878108024597, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.09237670898438, "min": -35.649871826171875, "max": 178.72816467285156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016246750950813293, "min": -0.015270182862877846, "max": 0.4299890398979187, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.532843589782715, "min": -4.199300289154053, "max": 101.90740203857422, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06831774079806305, "min": 0.0650464206922888, "max": 0.07536069761808963, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9564483711728827, "min": 0.5275248833266274, "max": 1.0781907369896278, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015307599947499554, "min": 0.000589934407466626, "max": 0.016088934076418364, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21430639926499376, "min": 0.006489278482132887, "max": 0.22394581279756187, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5612546224714245e-06, "min": 7.5612546224714245e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010585756471459994, "min": 0.00010585756471459994, "max": 0.0035076671307776998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025203857142857, "min": 0.1025203857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352854, "min": 1.3886848, "max": 2.5726338, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026178653285714276, "min": 0.00026178653285714276, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036650114599999983, "min": 0.0036650114599999983, "max": 0.11694530776999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010998918674886227, "min": 0.010998918674886227, "max": 0.5137199759483337, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15398485958576202, "min": 0.15398485958576202, "max": 3.5960397720336914, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 332.1847826086956, "min": 287.4950495049505, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30561.0, "min": 15984.0, "max": 32485.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5872131790761108, "min": -1.0000000521540642, "max": 1.6728831537731803, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.4363992959261, "min": -30.998001605272293, "max": 168.9611985310912, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5872131790761108, "min": -1.0000000521540642, "max": 1.6728831537731803, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.4363992959261, "min": -30.998001605272293, "max": 168.9611985310912, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03672671936334694, "min": 0.03385886115094763, "max": 11.483795637264848, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3421314620645717, "min": 3.3421314620645717, "max": 183.74073019623756, "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": "1695617951", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695620367" }, "total": 2416.220862628, "count": 1, "self": 0.5392859059998045, "children": { "run_training.setup": { "total": 0.06932937499999525, "count": 1, "self": 0.06932937499999525 }, "TrainerController.start_learning": { "total": 2415.612247347, "count": 1, "self": 1.5600894099816287, "children": { "TrainerController._reset_env": { "total": 5.308189666999965, "count": 1, "self": 5.308189666999965 }, "TrainerController.advance": { "total": 2408.651175196018, "count": 64108, "self": 1.5371991809934116, "children": { "env_step": { "total": 1744.24342826201, "count": 64108, "self": 1627.2005873490605, "children": { "SubprocessEnvManager._take_step": { "total": 116.11415176297675, "count": 64108, "self": 4.980430711962356, "children": { "TorchPolicy.evaluate": { "total": 111.13372105101439, "count": 62578, "self": 111.13372105101439 } } }, "workers": { "total": 0.9286891499727972, "count": 64108, "self": 0.0, "children": { "worker_root": { "total": 2409.9519690219604, "count": 64108, "is_parallel": true, "self": 905.9661975189692, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010266027000000122, "count": 1, "is_parallel": true, "self": 0.008214946000009604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020510809999905177, "count": 8, "is_parallel": true, "self": 0.0020510809999905177 } } }, "UnityEnvironment.step": { "total": 0.05368223600004285, "count": 1, "is_parallel": true, "self": 0.0006353500000955137, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005313169999681122, "count": 1, "is_parallel": true, "self": 0.0005313169999681122 }, "communicator.exchange": { "total": 0.04939793099998724, "count": 1, "is_parallel": true, "self": 0.04939793099998724 }, "steps_from_proto": { "total": 0.0031176379999919845, "count": 1, "is_parallel": true, "self": 0.0004217640000092615, "children": { "_process_rank_one_or_two_observation": { "total": 0.002695873999982723, "count": 8, "is_parallel": true, "self": 0.002695873999982723 } } } } } } }, "UnityEnvironment.step": { "total": 1503.9857715029912, "count": 64107, "is_parallel": true, "self": 35.552223712086516, "children": { "UnityEnvironment._generate_step_input": { "total": 24.603260711994153, "count": 64107, "is_parallel": true, "self": 24.603260711994153 }, "communicator.exchange": { "total": 1329.4033270339519, "count": 64107, "is_parallel": true, "self": 1329.4033270339519 }, "steps_from_proto": { "total": 114.4269600449586, "count": 64107, "is_parallel": true, "self": 23.12961105901934, "children": { "_process_rank_one_or_two_observation": { "total": 91.29734898593927, "count": 512856, "is_parallel": true, "self": 91.29734898593927 } } } } } } } } } } }, "trainer_advance": { "total": 662.8705477530148, "count": 64108, "self": 2.9172799540575625, "children": { "process_trajectory": { "total": 118.61554389995797, "count": 64108, "self": 118.40732350995802, "children": { "RLTrainer._checkpoint": { "total": 0.2082203899999513, "count": 2, "self": 0.2082203899999513 } } }, "_update_policy": { "total": 541.3377238989992, "count": 452, "self": 354.39823796799317, "children": { "TorchPPOOptimizer.update": { "total": 186.93948593100606, "count": 22815, "self": 186.93948593100606 } } } } } } }, "trainer_threads": { "total": 1.018000148178544e-06, "count": 1, "self": 1.018000148178544e-06 }, "TrainerController._save_models": { "total": 0.09279205600023488, "count": 1, "self": 0.0014201980002326309, "children": { "RLTrainer._checkpoint": { "total": 0.09137185800000225, "count": 1, "self": 0.09137185800000225 } } } } } } }