{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5353277325630188, "min": 0.5353277325630188, "max": 1.475871205329895, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16034.13671875, "min": 16034.13671875, "max": 44772.02734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989916.0, "min": 29882.0, "max": 989916.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989916.0, "min": 29882.0, "max": 989916.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3012092709541321, "min": -0.12279359251260757, "max": 0.30525824427604675, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 77.10957336425781, "min": -29.5932559967041, "max": 80.58817291259766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029363010078668594, "min": 0.0012516822898760438, "max": 0.3825514316558838, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.51693058013916, "min": 0.3179273009300232, "max": 90.66468811035156, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06926548547274172, "min": 0.0643377494787946, "max": 0.07337055569570068, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9697167966183841, "min": 0.5036782812883799, "max": 1.069606152974302, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011229231258318581, "min": 0.00038680095713888326, "max": 0.012697830827609221, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15720923761646013, "min": 0.004254810528527716, "max": 0.1904674624141383, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.302826137185713e-06, "min": 7.302826137185713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010223956592059998, "min": 0.00010223956592059998, "max": 0.0035082443305853, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243424285714287, "min": 0.10243424285714287, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340794000000001, "min": 1.3886848, "max": 2.5694147000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002531808614285714, "min": 0.0002531808614285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035445320599999997, "min": 0.0035445320599999997, "max": 0.11696452853000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011185184121131897, "min": 0.011185184121131897, "max": 0.4553283154964447, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15659257769584656, "min": 0.15659257769584656, "max": 3.18729829788208, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 530.4615384615385, "min": 523.5666666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27584.0, "min": 16809.0, "max": 32391.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2387038142635272, "min": -0.9999742455059483, "max": 1.2430399637669325, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.41259834170341, "min": -30.999201610684395, "max": 74.58239782601595, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2387038142635272, "min": -0.9999742455059483, "max": 1.2430399637669325, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.41259834170341, "min": -30.999201610684395, "max": 74.58239782601595, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.061457484152365044, "min": 0.061457484152365044, "max": 9.137401564156308, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1957891759229824, "min": 3.1957891759229824, "max": 155.33582659065723, "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": "1710363181", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710364996" }, "total": 1814.4316346009996, "count": 1, "self": 0.37728766199961683, "children": { "run_training.setup": { "total": 0.052258174999678886, "count": 1, "self": 0.052258174999678886 }, "TrainerController.start_learning": { "total": 1814.0020887640003, "count": 1, "self": 1.606278955968719, "children": { "TrainerController._reset_env": { "total": 2.1585847960000137, "count": 1, "self": 2.1585847960000137 }, "TrainerController.advance": { "total": 1810.148427440031, "count": 63359, "self": 1.5901242840727718, "children": { "env_step": { "total": 1204.4690544179293, "count": 63359, "self": 1061.9646168667855, "children": { "SubprocessEnvManager._take_step": { "total": 141.4925858690308, "count": 63359, "self": 5.135585090047243, "children": { "TorchPolicy.evaluate": { "total": 136.35700077898355, "count": 62553, "self": 136.35700077898355 } } }, "workers": { "total": 1.011851682113047, "count": 63359, "self": 0.0, "children": { "worker_root": { "total": 1811.4356805799166, "count": 63359, "is_parallel": true, "self": 867.957377457973, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023316440001508454, "count": 1, "is_parallel": true, "self": 0.0006746229996679176, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016570210004829278, "count": 8, "is_parallel": true, "self": 0.0016570210004829278 } } }, "UnityEnvironment.step": { "total": 0.040314954000223224, "count": 1, "is_parallel": true, "self": 0.00044979200038142153, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032484599978488404, "count": 1, "is_parallel": true, "self": 0.00032484599978488404 }, "communicator.exchange": { "total": 0.03839946400012195, "count": 1, "is_parallel": true, "self": 0.03839946400012195 }, "steps_from_proto": { "total": 0.0011408519999349664, "count": 1, "is_parallel": true, "self": 0.0002619639999466017, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008788879999883648, "count": 8, "is_parallel": true, "self": 0.0008788879999883648 } } } } } } }, "UnityEnvironment.step": { "total": 943.4783031219436, "count": 63358, "is_parallel": true, "self": 26.041625976035448, "children": { "UnityEnvironment._generate_step_input": { "total": 17.322087656973054, "count": 63358, "is_parallel": true, "self": 17.322087656973054 }, "communicator.exchange": { "total": 825.1761111309843, "count": 63358, "is_parallel": true, "self": 825.1761111309843 }, "steps_from_proto": { "total": 74.93847835795077, "count": 63358, "is_parallel": true, "self": 16.50608037939628, "children": { "_process_rank_one_or_two_observation": { "total": 58.43239797855449, "count": 506864, "is_parallel": true, "self": 58.43239797855449 } } } } } } } } } } }, "trainer_advance": { "total": 604.0892487380288, "count": 63359, "self": 3.1215421109855015, "children": { "process_trajectory": { "total": 121.86970277403998, "count": 63359, "self": 121.66743374703947, "children": { "RLTrainer._checkpoint": { "total": 0.20226902700051141, "count": 2, "self": 0.20226902700051141 } } }, "_update_policy": { "total": 479.0980038530033, "count": 449, "self": 278.72414770100204, "children": { "TorchPPOOptimizer.update": { "total": 200.37385615200128, "count": 22764, "self": 200.37385615200128 } } } } } } }, "trainer_threads": { "total": 9.980003596865572e-07, "count": 1, "self": 9.980003596865572e-07 }, "TrainerController._save_models": { "total": 0.08879657400029828, "count": 1, "self": 0.001519106000159809, "children": { "RLTrainer._checkpoint": { "total": 0.08727746800013847, "count": 1, "self": 0.08727746800013847 } } } } } } }