{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47683796286582947, "min": 0.4645557105541229, "max": 1.4066835641860962, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14396.69140625, "min": 13872.2109375, "max": 42673.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48158687353134155, "min": -0.0967249721288681, "max": 0.5100737810134888, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 133.39956665039062, "min": -23.310718536376953, "max": 142.3105926513672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007210755255073309, "min": -0.0056979116052389145, "max": 0.5905563235282898, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.997379183769226, "min": -1.418779969215393, "max": 139.96185302734375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07000353229156316, "min": 0.06495309833927161, "max": 0.07432617950362522, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9800494520818841, "min": 0.4931474569947432, "max": 1.0768770674436452, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018072356013887687, "min": 0.0005952741028856629, "max": 0.018072356013887687, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.25301298419442764, "min": 0.007143289234627955, "max": 0.25301298419442764, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.609276035035713e-06, "min": 7.609276035035713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010652986449049999, "min": 0.00010652986449049999, "max": 0.0036325945891351997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253639285714287, "min": 0.10253639285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4355095000000002, "min": 1.3691136000000002, "max": 2.6108648, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002633856464285714, "min": 0.0002633856464285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036873990499999994, "min": 0.0036873990499999994, "max": 0.12110539352000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008289298973977566, "min": 0.008289298973977566, "max": 0.4192163944244385, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11605018377304077, "min": 0.11605018377304077, "max": 2.9345147609710693, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 354.92857142857144, "min": 354.92857142857144, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29814.0, "min": 15984.0, "max": 32652.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5259999808456217, "min": -1.0000000521540642, "max": 1.540740725894769, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.18399839103222, "min": -32.000001668930054, "max": 128.18399839103222, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5259999808456217, "min": -1.0000000521540642, "max": 1.540740725894769, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.18399839103222, "min": -32.000001668930054, "max": 128.18399839103222, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03081121647669317, "min": 0.03081121647669317, "max": 9.0253397366032, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5881421840422263, "min": 2.457729238405591, "max": 144.4054357856512, "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": "1694422689", "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": "1694425049" }, "total": 2360.3881461319997, "count": 1, "self": 0.4762609129993507, "children": { "run_training.setup": { "total": 0.06443426200007707, "count": 1, "self": 0.06443426200007707 }, "TrainerController.start_learning": { "total": 2359.847450957, "count": 1, "self": 1.7680704709796373, "children": { "TrainerController._reset_env": { "total": 5.201811085999907, "count": 1, "self": 5.201811085999907 }, "TrainerController.advance": { "total": 2352.7735764460203, "count": 63781, "self": 1.8502823469543728, "children": { "env_step": { "total": 1670.1564918940148, "count": 63781, "self": 1542.2684043579854, "children": { "SubprocessEnvManager._take_step": { "total": 126.83050053596071, "count": 63781, "self": 5.42830568394038, "children": { "TorchPolicy.evaluate": { "total": 121.40219485202033, "count": 62569, "self": 121.40219485202033 } } }, "workers": { "total": 1.0575870000686791, "count": 63781, "self": 0.0, "children": { "worker_root": { "total": 2353.8136250359757, "count": 63781, "is_parallel": true, "self": 944.6669469330279, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0032000950000110606, "count": 1, "is_parallel": true, "self": 0.0009001180001178, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022999769998932607, "count": 8, "is_parallel": true, "self": 0.0022999769998932607 } } }, "UnityEnvironment.step": { "total": 0.056316693000098894, "count": 1, "is_parallel": true, "self": 0.0005746570000155771, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005532239999865851, "count": 1, "is_parallel": true, "self": 0.0005532239999865851 }, "communicator.exchange": { "total": 0.05320728100014094, "count": 1, "is_parallel": true, "self": 0.05320728100014094 }, "steps_from_proto": { "total": 0.001981530999955794, "count": 1, "is_parallel": true, "self": 0.00039006199995128554, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015914690000045084, "count": 8, "is_parallel": true, "self": 0.0015914690000045084 } } } } } } }, "UnityEnvironment.step": { "total": 1409.1466781029478, "count": 63780, "is_parallel": true, "self": 36.786904295868226, "children": { "UnityEnvironment._generate_step_input": { "total": 26.281768341023508, "count": 63780, "is_parallel": true, "self": 26.281768341023508 }, "communicator.exchange": { "total": 1225.4409840390463, "count": 63780, "is_parallel": true, "self": 1225.4409840390463 }, "steps_from_proto": { "total": 120.63702142700981, "count": 63780, "is_parallel": true, "self": 24.526910072966984, "children": { "_process_rank_one_or_two_observation": { "total": 96.11011135404283, "count": 510240, "is_parallel": true, "self": 96.11011135404283 } } } } } } } } } } }, "trainer_advance": { "total": 680.7668022050509, "count": 63781, "self": 3.1572992850835817, "children": { "process_trajectory": { "total": 122.6213580849701, "count": 63781, "self": 122.33212351997031, "children": { "RLTrainer._checkpoint": { "total": 0.28923456499978784, "count": 2, "self": 0.28923456499978784 } } }, "_update_policy": { "total": 554.9881448349972, "count": 451, "self": 361.71402244001797, "children": { "TorchPPOOptimizer.update": { "total": 193.27412239497926, "count": 22803, "self": 193.27412239497926 } } } } } } }, "trainer_threads": { "total": 8.960000741353724e-07, "count": 1, "self": 8.960000741353724e-07 }, "TrainerController._save_models": { "total": 0.10399205800013078, "count": 1, "self": 0.001534943000478961, "children": { "RLTrainer._checkpoint": { "total": 0.10245711499965182, "count": 1, "self": 0.10245711499965182 } } } } } } }