{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29915913939476013, "min": 0.28410860896110535, "max": 1.5636372566223145, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8879.04296875, "min": 8564.169921875, "max": 47434.5, "count": 50 }, "Pyramids.Step.mean": { "value": 1499986.0, "min": 29952.0, "max": 1499986.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499986.0, "min": 29952.0, "max": 1499986.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6056761145591736, "min": -0.09941365569829941, "max": 0.70343017578125, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 171.40634155273438, "min": -23.859277725219727, "max": 203.29132080078125, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029083063825964928, "min": -0.05323021486401558, "max": 0.046292513608932495, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.230506896972656, "min": -12.615560531616211, "max": 11.156496047973633, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06749800125059362, "min": 0.0645788092425348, "max": 0.07387033428642012, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9449720175083106, "min": 0.5122415571954924, "max": 1.0787357757867808, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01635693196329244, "min": 5.1410141096389446e-05, "max": 0.018066525813386157, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22899704748609415, "min": 0.0006683318342530628, "max": 0.2529313613874062, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.920927597819051e-06, "min": 2.920927597819051e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.0892986369466716e-05, "min": 4.0892986369466716e-05, "max": 0.0033499776833407994, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10097360952380953, "min": 0.10097360952380953, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4136305333333334, "min": 1.3924565333333336, "max": 2.4779453999999994, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00010726359142857153, "min": 0.00010726359142857153, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015016902800000015, "min": 0.0015016902800000015, "max": 0.11167425408, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.003088225843384862, "min": 0.003088225843384862, "max": 0.08980808407068253, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.043235160410404205, "min": 0.043235160410404205, "max": 0.6286565661430359, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.61052631578946, "min": 260.6371681415929, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27988.0, "min": 15984.0, "max": 32331.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6632673507458284, "min": -1.0000000521540642, "max": 1.7258411051235467, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.0103983208537, "min": -31.99920167028904, "max": 192.54659831523895, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6632673507458284, "min": -1.0000000521540642, "max": 1.7258411051235467, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.0103983208537, "min": -31.99920167028904, "max": 192.54659831523895, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.00949731385720186, "min": 0.00925837562298294, "max": 2.0735077019780874, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 0.9022448164341768, "min": 0.9022448164341768, "max": 33.1761232316494, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692519392", "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 2 --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": "1692522895" }, "total": 3502.9596972140007, "count": 1, "self": 0.47587667900006636, "children": { "run_training.setup": { "total": 0.03943244499987486, "count": 1, "self": 0.03943244499987486 }, "TrainerController.start_learning": { "total": 3502.4443880900008, "count": 1, "self": 2.1719298980442545, "children": { "TrainerController._reset_env": { "total": 3.9438994219999586, "count": 1, "self": 3.9438994219999586 }, "TrainerController.advance": { "total": 3496.227934853957, "count": 96019, "self": 2.1923658319446986, "children": { "env_step": { "total": 2496.282318781954, "count": 96019, "self": 2323.6505030061444, "children": { "SubprocessEnvManager._take_step": { "total": 171.34090609513623, "count": 96019, "self": 7.490892098382574, "children": { "TorchPolicy.evaluate": { "total": 163.85001399675366, "count": 93816, "self": 163.85001399675366 } } }, "workers": { "total": 1.2909096806733942, "count": 96019, "self": 0.0, "children": { "worker_root": { "total": 3494.2376615598205, "count": 96019, "is_parallel": true, "self": 1354.1216041257712, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019422639998083469, "count": 1, "is_parallel": true, "self": 0.0006881150011395221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012541489986688248, "count": 8, "is_parallel": true, "self": 0.0012541489986688248 } } }, "UnityEnvironment.step": { "total": 0.05570035900018411, "count": 1, "is_parallel": true, "self": 0.0006343960003505345, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006096659999457188, "count": 1, "is_parallel": true, "self": 0.0006096659999457188 }, "communicator.exchange": { "total": 0.05234674700022879, "count": 1, "is_parallel": true, "self": 0.05234674700022879 }, "steps_from_proto": { "total": 0.002109549999659066, "count": 1, "is_parallel": true, "self": 0.0004419409997353796, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016676089999236865, "count": 8, "is_parallel": true, "self": 0.0016676089999236865 } } } } } } }, "UnityEnvironment.step": { "total": 2140.1160574340493, "count": 96018, "is_parallel": true, "self": 52.06851173504401, "children": { "UnityEnvironment._generate_step_input": { "total": 36.57885612815335, "count": 96018, "is_parallel": true, "self": 36.57885612815335 }, "communicator.exchange": { "total": 1881.6948344339062, "count": 96018, "is_parallel": true, "self": 1881.6948344339062 }, "steps_from_proto": { "total": 169.7738551369457, "count": 96018, "is_parallel": true, "self": 34.172791839220736, "children": { "_process_rank_one_or_two_observation": { "total": 135.60106329772498, "count": 768144, "is_parallel": true, "self": 135.60106329772498 } } } } } } } } } } }, "trainer_advance": { "total": 997.7532502400582, "count": 96019, "self": 4.0224143680216, "children": { "process_trajectory": { "total": 174.90187697804777, "count": 96019, "self": 174.59119515204748, "children": { "RLTrainer._checkpoint": { "total": 0.31068182600029104, "count": 3, "self": 0.31068182600029104 } } }, "_update_policy": { "total": 818.8289588939888, "count": 675, "self": 536.3215708619209, "children": { "TorchPPOOptimizer.update": { "total": 282.50738803206787, "count": 34212, "self": 282.50738803206787 } } } } } } }, "trainer_threads": { "total": 1.0139992809854448e-06, "count": 1, "self": 1.0139992809854448e-06 }, "TrainerController._save_models": { "total": 0.1006229020003957, "count": 1, "self": 0.0015464750013052253, "children": { "RLTrainer._checkpoint": { "total": 0.09907642699909047, "count": 1, "self": 0.09907642699909047 } } } } } } }