{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5534970760345459, "min": 0.5534970760345459, "max": 1.413807988166809, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16835.16796875, "min": 16835.16796875, "max": 42889.27734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989976.0, "min": 29876.0, "max": 989976.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989976.0, "min": 29876.0, "max": 989976.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2775384783744812, "min": -0.11032278090715408, "max": 0.295678973197937, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 71.8824691772461, "min": -26.477466583251953, "max": 76.58085632324219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0013886155793443322, "min": -0.0017076353542506695, "max": 0.39094293117523193, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.35965144634246826, "min": -0.4371546506881714, "max": 94.21724700927734, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06754765192384919, "min": 0.06478568333886232, "max": 0.07358575871208399, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9456671269338888, "min": 0.480868295816425, "max": 1.0548193030037651, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012538805685922161, "min": 0.0004524768144623889, "max": 0.012538805685922161, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17554327960291025, "min": 0.005882198588011056, "max": 0.17554327960291025, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5860688999142866e-06, "min": 7.5860688999142866e-06, "max": 0.0002952361730165143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001062049645988, "min": 0.0001062049645988, "max": 0.0033822119725960996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252865714285715, "min": 0.10252865714285715, "max": 0.19841205714285715, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354012, "min": 1.3888844, "max": 2.5274039000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026261284857142863, "min": 0.00026261284857142863, "max": 0.009841364508571428, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003676579880000001, "min": 0.003676579880000001, "max": 0.11276764961, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015340897254645824, "min": 0.015158257447183132, "max": 0.6246576309204102, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.214772567152977, "min": 0.2122156023979187, "max": 4.372603416442871, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 527.457627118644, "min": 527.457627118644, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31120.0, "min": 16675.0, "max": 33764.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1703016634209682, "min": -1.0000000521540642, "max": 1.1703016634209682, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 69.04779814183712, "min": -32.000001668930054, "max": 69.04779814183712, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1703016634209682, "min": -1.0000000521540642, "max": 1.1703016634209682, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 69.04779814183712, "min": -32.000001668930054, "max": 69.04779814183712, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08352777892151468, "min": 0.08352777892151468, "max": 12.897804009563783, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.9281389563693665, "min": 4.471724841743708, "max": 219.2626681625843, "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": "1683117636", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "1683119745" }, "total": 2109.166025959, "count": 1, "self": 0.8892989739997574, "children": { "run_training.setup": { "total": 0.04589672600002359, "count": 1, "self": 0.04589672600002359 }, "TrainerController.start_learning": { "total": 2108.230830259, "count": 1, "self": 1.6261907840053027, "children": { "TrainerController._reset_env": { "total": 3.885810552999942, "count": 1, "self": 3.885810552999942 }, "TrainerController.advance": { "total": 2102.575042304995, "count": 63340, "self": 1.5350413809892416, "children": { "env_step": { "total": 1467.849041044005, "count": 63340, "self": 1351.0322012389936, "children": { "SubprocessEnvManager._take_step": { "total": 115.92192970497524, "count": 63340, "self": 4.876847897958214, "children": { "TorchPolicy.evaluate": { "total": 111.04508180701703, "count": 62571, "self": 111.04508180701703 } } }, "workers": { "total": 0.8949101000360997, "count": 63340, "self": 0.0, "children": { "worker_root": { "total": 2103.3071255419727, "count": 63340, "is_parallel": true, "self": 868.1651775269902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0015664500000411863, "count": 1, "is_parallel": true, "self": 0.0004160910000337026, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011503590000074837, "count": 8, "is_parallel": true, "self": 0.0011503590000074837 } } }, "UnityEnvironment.step": { "total": 0.07389690299999074, "count": 1, "is_parallel": true, "self": 0.0005345690001377079, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004652220000025409, "count": 1, "is_parallel": true, "self": 0.0004652220000025409 }, "communicator.exchange": { "total": 0.07126625799992325, "count": 1, "is_parallel": true, "self": 0.07126625799992325 }, "steps_from_proto": { "total": 0.0016308539999272398, "count": 1, "is_parallel": true, "self": 0.00035983199984457315, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012710220000826666, "count": 8, "is_parallel": true, "self": 0.0012710220000826666 } } } } } } }, "UnityEnvironment.step": { "total": 1235.1419480149825, "count": 63339, "is_parallel": true, "self": 31.906596027058185, "children": { "UnityEnvironment._generate_step_input": { "total": 22.5041934649488, "count": 63339, "is_parallel": true, "self": 22.5041934649488 }, "communicator.exchange": { "total": 1083.3254884010262, "count": 63339, "is_parallel": true, "self": 1083.3254884010262 }, "steps_from_proto": { "total": 97.40567012194913, "count": 63339, "is_parallel": true, "self": 20.291918079078187, "children": { "_process_rank_one_or_two_observation": { "total": 77.11375204287094, "count": 506712, "is_parallel": true, "self": 77.11375204287094 } } } } } } } } } } }, "trainer_advance": { "total": 633.1909598800007, "count": 63340, "self": 2.7233101200291685, "children": { "process_trajectory": { "total": 104.95484383497399, "count": 63340, "self": 104.63889837997397, "children": { "RLTrainer._checkpoint": { "total": 0.31594545500001914, "count": 2, "self": 0.31594545500001914 } } }, "_update_policy": { "total": 525.5128059249976, "count": 444, "self": 338.5455011309914, "children": { "TorchPPOOptimizer.update": { "total": 186.96730479400617, "count": 22830, "self": 186.96730479400617 } } } } } } }, "trainer_threads": { "total": 1.2269997569092084e-06, "count": 1, "self": 1.2269997569092084e-06 }, "TrainerController._save_models": { "total": 0.14378539000017554, "count": 1, "self": 0.0019694910001817334, "children": { "RLTrainer._checkpoint": { "total": 0.1418158989999938, "count": 1, "self": 0.1418158989999938 } } } } } } }