{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.27636849880218506, "min": 0.21948161721229553, "max": 1.4347002506256104, "count": 44 }, "Pyramids.Policy.Entropy.sum": { "value": 8352.9619140625, "min": 6570.40185546875, "max": 43523.06640625, "count": 44 }, "Pyramids.Step.mean": { "value": 1319878.0, "min": 29952.0, "max": 1319878.0, "count": 44 }, "Pyramids.Step.sum": { "value": 1319878.0, "min": 29952.0, "max": 1319878.0, "count": 44 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6449220776557922, "min": -0.09800910949707031, "max": 0.7112522721290588, "count": 44 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.15786743164062, "min": -23.522186279296875, "max": 201.28439331054688, "count": 44 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.021253304556012154, "min": -0.01324627734720707, "max": 0.47120195627212524, "count": 44 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.035938262939453, "min": -3.5367560386657715, "max": 111.67486572265625, "count": 44 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06630620382564197, "min": 0.06630620382564197, "max": 0.07674029782774386, "count": 44 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9282868535589874, "min": 0.5014012135901815, "max": 1.030918829065437, "count": 44 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01464766908449949, "min": 0.0004860912368682317, "max": 0.017093823789244716, "count": 44 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20506736718299284, "min": 0.006805277316155244, "max": 0.23931353304942604, "count": 44 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00016948878636089524, "min": 0.00016948878636089524, "max": 0.00029838354339596195, "count": 44 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0023728430090525334, "min": 0.0020691136102954665, "max": 0.003969326976891033, "count": 44 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15649624761904762, "min": 0.15649624761904762, "max": 0.19946118095238097, "count": 44 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1909474666666666, "min": 1.3897045333333333, "max": 2.7824350000000004, "count": 44 }, "Pyramids.Policy.Beta.mean": { "value": 0.005653975137142858, "min": 0.005653975137142858, "max": 0.009946171977142856, "count": 44 }, "Pyramids.Policy.Beta.sum": { "value": 0.07915565192000001, "min": 0.06897148288, "max": 0.13231858577000002, "count": 44 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014192720875144005, "min": 0.0137877706438303, "max": 0.5870365500450134, "count": 44 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19869808852672577, "min": 0.19407819211483002, "max": 4.109255790710449, "count": 44 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 286.7647058823529, "min": 266.8407079646018, "max": 999.0, "count": 44 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29250.0, "min": 15984.0, "max": 32513.0, "count": 44 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.713235274395522, "min": -1.0000000521540642, "max": 1.7154530860417712, "count": 44 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.74999798834324, "min": -32.000001668930054, "max": 193.84619872272015, "count": 44 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.713235274395522, "min": -1.0000000521540642, "max": 1.7154530860417712, "count": 44 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.74999798834324, "min": -32.000001668930054, "max": 193.84619872272015, "count": 44 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04262612909751981, "min": 0.04078012996969283, "max": 11.879976375028491, "count": 44 }, "Pyramids.Policy.RndReward.sum": { "value": 4.34786516794702, "min": 4.119438842324598, "max": 190.07962200045586, "count": 44 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 44 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 44 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686937422", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686940657" }, "total": 3235.3512502599997, "count": 1, "self": 0.4930358489991704, "children": { "run_training.setup": { "total": 0.06502566700009993, "count": 1, "self": 0.06502566700009993 }, "TrainerController.start_learning": { "total": 3234.7931887440004, "count": 1, "self": 2.143951727048261, "children": { "TrainerController._reset_env": { "total": 4.526815659000022, "count": 1, "self": 4.526815659000022 }, "TrainerController.advance": { "total": 3228.119490025952, "count": 84508, "self": 2.025419573036743, "children": { "env_step": { "total": 2347.396944688907, "count": 84508, "self": 2188.7344632557956, "children": { "SubprocessEnvManager._take_step": { "total": 157.3948232290877, "count": 84508, "self": 6.708448955064796, "children": { "TorchPolicy.evaluate": { "total": 150.6863742740229, "count": 82615, "self": 150.6863742740229 } } }, "workers": { "total": 1.267658204023519, "count": 84508, "self": 0.0, "children": { "worker_root": { "total": 3226.952751420022, "count": 84508, "is_parallel": true, "self": 1201.778025288977, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018934419999823149, "count": 1, "is_parallel": true, "self": 0.0005892039985155861, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013042380014667287, "count": 8, "is_parallel": true, "self": 0.0013042380014667287 } } }, "UnityEnvironment.step": { "total": 0.049936512999920524, "count": 1, "is_parallel": true, "self": 0.0006025040001986781, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005034179998801847, "count": 1, "is_parallel": true, "self": 0.0005034179998801847 }, "communicator.exchange": { "total": 0.04679708599996957, "count": 1, "is_parallel": true, "self": 0.04679708599996957 }, "steps_from_proto": { "total": 0.0020335049998720933, "count": 1, "is_parallel": true, "self": 0.00039019099949655356, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016433140003755398, "count": 8, "is_parallel": true, "self": 0.0016433140003755398 } } } } } } }, "UnityEnvironment.step": { "total": 2025.1747261310452, "count": 84507, "is_parallel": true, "self": 47.241338157004975, "children": { "UnityEnvironment._generate_step_input": { "total": 31.82058965401893, "count": 84507, "is_parallel": true, "self": 31.82058965401893 }, "communicator.exchange": { "total": 1803.5211645140007, "count": 84507, "is_parallel": true, "self": 1803.5211645140007 }, "steps_from_proto": { "total": 142.59163380602058, "count": 84507, "is_parallel": true, "self": 28.485915084717817, "children": { "_process_rank_one_or_two_observation": { "total": 114.10571872130276, "count": 676056, "is_parallel": true, "self": 114.10571872130276 } } } } } } } } } } }, "trainer_advance": { "total": 878.6971257640084, "count": 84508, "self": 3.8622924179567235, "children": { "process_trajectory": { "total": 151.85651801605854, "count": 84508, "self": 151.5926730380579, "children": { "RLTrainer._checkpoint": { "total": 0.263844978000634, "count": 2, "self": 0.263844978000634 } } }, "_update_policy": { "total": 722.9783153299932, "count": 600, "self": 463.186853125022, "children": { "TorchPPOOptimizer.update": { "total": 259.79146220497114, "count": 30167, "self": 259.79146220497114 } } } } } } }, "trainer_threads": { "total": 1.309999788645655e-06, "count": 1, "self": 1.309999788645655e-06 }, "TrainerController._save_models": { "total": 0.002930022000327881, "count": 1, "self": 2.778000089165289e-05, "children": { "RLTrainer._checkpoint": { "total": 0.002902241999436228, "count": 1, "self": 0.002902241999436228 } } } } } } }