{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46760785579681396, "min": 0.46760785579681396, "max": 1.501516580581665, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13960.900390625, "min": 13960.900390625, "max": 45550.0078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989970.0, "min": 29952.0, "max": 989970.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6204172968864441, "min": -0.09470121562480927, "max": 0.6359407305717468, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.95767211914062, "min": -22.8229923248291, "max": 179.97122192382812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03943268209695816, "min": 0.0018938126740977168, "max": 0.3217858076095581, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.120016098022461, "min": 0.4715593457221985, "max": 76.26323699951172, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06498471974723158, "min": 0.06408514233054305, "max": 0.07437456883538592, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9747707962084736, "min": 0.5018065789175533, "max": 1.0884324947221422, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014461192886593897, "min": 0.00029827680278959694, "max": 0.01497814462392435, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21691789329890845, "min": 0.0032810448306855662, "max": 0.21691789329890845, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.462457512546665e-06, "min": 7.462457512546665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011193686268819998, "min": 0.00011193686268819998, "max": 0.0035081126306291998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248745333333335, "min": 0.10248745333333335, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373118000000003, "min": 1.3886848, "max": 2.5693708, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025849658799999997, "min": 0.00025849658799999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038774488199999997, "min": 0.0038774488199999997, "max": 0.11696014292, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011370858177542686, "min": 0.011370858177542686, "max": 0.40791645646095276, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17056287825107574, "min": 0.16179035604000092, "max": 2.855415105819702, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 317.3, "min": 297.2916666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31730.0, "min": 15984.0, "max": 32759.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.638984147791225, "min": -1.0000000521540642, "max": 1.7072736719721242, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.53739892691374, "min": -30.996601596474648, "max": 165.53739892691374, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.638984147791225, "min": -1.0000000521540642, "max": 1.7072736719721242, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.53739892691374, "min": -30.996601596474648, "max": 165.53739892691374, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03799675231828875, "min": 0.03487860877112804, "max": 8.502329995855689, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.837671984147164, "min": 3.313467833257164, "max": 136.03727993369102, "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": "1770755850", "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": "1770759541" }, "total": 3690.482081139, "count": 1, "self": 1.3861758550010563, "children": { "run_training.setup": { "total": 0.046169187000487, "count": 1, "self": 0.046169187000487 }, "TrainerController.start_learning": { "total": 3689.0497360969985, "count": 1, "self": 2.5784604100335855, "children": { "TrainerController._reset_env": { "total": 3.3637599849989783, "count": 1, "self": 3.3637599849989783 }, "TrainerController.advance": { "total": 3682.960828145966, "count": 63797, "self": 2.5688477633011644, "children": { "env_step": { "total": 2532.026782191855, "count": 63797, "self": 2355.4400213304907, "children": { "SubprocessEnvManager._take_step": { "total": 175.0932828336281, "count": 63797, "self": 7.972021730498454, "children": { "TorchPolicy.evaluate": { "total": 167.12126110312965, "count": 62567, "self": 167.12126110312965 } } }, "workers": { "total": 1.4934780277362734, "count": 63797, "self": 0.0, "children": { "worker_root": { "total": 3679.63137843408, "count": 63797, "is_parallel": true, "self": 1521.554666676213, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002424050000627176, "count": 1, "is_parallel": true, "self": 0.0006969930018385639, "children": { "_process_rank_one_or_two_observation": { "total": 0.001727056998788612, "count": 8, "is_parallel": true, "self": 0.001727056998788612 } } }, "UnityEnvironment.step": { "total": 0.07853432999945653, "count": 1, "is_parallel": true, "self": 0.000667635000354494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005478949988173554, "count": 1, "is_parallel": true, "self": 0.0005478949988173554 }, "communicator.exchange": { "total": 0.07509799900071812, "count": 1, "is_parallel": true, "self": 0.07509799900071812 }, "steps_from_proto": { "total": 0.0022208009995665634, "count": 1, "is_parallel": true, "self": 0.0004616900005203206, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017591109990462428, "count": 8, "is_parallel": true, "self": 0.0017591109990462428 } } } } } } }, "UnityEnvironment.step": { "total": 2158.076711757867, "count": 63796, "is_parallel": true, "self": 49.59074895568483, "children": { "UnityEnvironment._generate_step_input": { "total": 32.53719220999301, "count": 63796, "is_parallel": true, "self": 32.53719220999301 }, "communicator.exchange": { "total": 1921.847789813275, "count": 63796, "is_parallel": true, "self": 1921.847789813275 }, "steps_from_proto": { "total": 154.10098077891416, "count": 63796, "is_parallel": true, "self": 31.203878667256504, "children": { "_process_rank_one_or_two_observation": { "total": 122.89710211165766, "count": 510368, "is_parallel": true, "self": 122.89710211165766 } } } } } } } } } } }, "trainer_advance": { "total": 1148.3651981908097, "count": 63797, "self": 4.852208379659714, "children": { "process_trajectory": { "total": 171.66109698012588, "count": 63797, "self": 171.26155225512593, "children": { "RLTrainer._checkpoint": { "total": 0.39954472499994154, "count": 2, "self": 0.39954472499994154 } } }, "_update_policy": { "total": 971.8518928310241, "count": 447, "self": 380.20127014905665, "children": { "TorchPPOOptimizer.update": { "total": 591.6506226819674, "count": 22767, "self": 591.6506226819674 } } } } } } }, "trainer_threads": { "total": 1.2780001270584762e-06, "count": 1, "self": 1.2780001270584762e-06 }, "TrainerController._save_models": { "total": 0.1466862779998337, "count": 1, "self": 0.007356153000728227, "children": { "RLTrainer._checkpoint": { "total": 0.13933012499910546, "count": 1, "self": 0.13933012499910546 } } } } } } }