{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3744937777519226, "min": 0.35644930601119995, "max": 0.820889413356781, "count": 23 }, "Pyramids.Policy.Entropy.sum": { "value": 11144.9345703125, "min": 10716.2919921875, "max": 24692.353515625, "count": 23 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 329889.0, "max": 989886.0, "count": 23 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 329889.0, "max": 989886.0, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.39457809925079346, "min": -0.08253936469554901, "max": 0.39457809925079346, "count": 23 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 104.56319427490234, "min": -19.891986846923828, "max": 104.56319427490234, "count": 23 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.025564437732100487, "min": -0.025564437732100487, "max": 0.04511326178908348, "count": 23 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.774576187133789, "min": -6.774576187133789, "max": 10.962522506713867, "count": 23 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0674477375846845, "min": 0.06511295669146681, "max": 0.07281731183978819, "count": 23 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9442683261855831, "min": 0.6630763047665358, "max": 1.0399824782798532, "count": 23 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012122288151514357, "min": 0.0009611697074516269, "max": 0.012610700131127875, "count": 23 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.169712034121201, "min": 0.011534036489419523, "max": 0.18405007849893687, "count": 23 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.556711766842858e-06, "min": 7.556711766842858e-06, "max": 0.00020492562169146999, "count": 23 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001057939647358, "min": 0.0001057939647358, "max": 0.0024986396671203, "count": 23 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251887142857143, "min": 0.10251887142857143, "max": 0.16830852999999996, "count": 23 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352642, "min": 1.4352642, "max": 2.2328797, "count": 23 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002616352557142858, "min": 0.0002616352557142858, "max": 0.006834022147, "count": 23 }, "Pyramids.Policy.Beta.sum": { "value": 0.003662893580000001, "min": 0.003662893580000001, "max": 0.08334468203, "count": 23 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0110855083912611, "min": 0.0110855083912611, "max": 0.03396270051598549, "count": 23 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1551971137523651, "min": 0.1551971137523651, "max": 0.39017587900161743, "count": 23 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 485.6, "min": 485.6, "max": 980.25, "count": 23 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31564.0, "min": 18380.0, "max": 32478.0, "count": 23 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2373753591225698, "min": -0.85615005181171, "max": 1.2724236981090853, "count": 23 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 80.42939834296703, "min": -27.39680165797472, "max": 80.42939834296703, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2373753591225698, "min": -0.85615005181171, "max": 1.2724236981090853, "count": 23 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 80.42939834296703, "min": -27.39680165797472, "max": 80.42939834296703, "count": 23 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05634882780991925, "min": 0.05634882780991925, "max": 0.34386324157056053, "count": 23 }, "Pyramids.Policy.RndReward.sum": { "value": 3.662673807644751, "min": 3.419767190818675, "max": 10.351330703124404, "count": 23 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1770600268", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 1- --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1770601778" }, "total": 1509.6666606159997, "count": 1, "self": 0.8436420190009812, "children": { "run_training.setup": { "total": 0.021299127000020235, "count": 1, "self": 0.021299127000020235 }, "TrainerController.start_learning": { "total": 1508.8017194699987, "count": 1, "self": 0.927150354569676, "children": { "TrainerController._reset_env": { "total": 2.694056038000781, "count": 1, "self": 2.694056038000781 }, "TrainerController.advance": { "total": 1505.0787303814304, "count": 44540, "self": 0.9622249445219495, "children": { "env_step": { "total": 1048.9855434837518, "count": 44540, "self": 946.3716842257891, "children": { "SubprocessEnvManager._take_step": { "total": 102.06356559412052, "count": 44540, "self": 3.202877071320472, "children": { "TorchPolicy.evaluate": { "total": 98.86068852280005, "count": 43816, "self": 98.86068852280005 } } }, "workers": { "total": 0.5502936638422398, "count": 44540, "self": 0.0, "children": { "worker_root": { "total": 1504.2441182311068, "count": 44540, "is_parallel": true, "self": 637.4337421761938, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002456062000419479, "count": 1, "is_parallel": true, "self": 0.0006841460017312784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017719159986882005, "count": 8, "is_parallel": true, "self": 0.0017719159986882005 } } }, "UnityEnvironment.step": { "total": 0.09175023499847157, "count": 1, "is_parallel": true, "self": 0.0005729769982281141, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004338199996709591, "count": 1, "is_parallel": true, "self": 0.0004338199996709591 }, "communicator.exchange": { "total": 0.08707945599962841, "count": 1, "is_parallel": true, "self": 0.08707945599962841 }, "steps_from_proto": { "total": 0.003663982000944088, "count": 1, "is_parallel": true, "self": 0.00034964199767273385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033143400032713544, "count": 8, "is_parallel": true, "self": 0.0033143400032713544 } } } } } } }, "UnityEnvironment.step": { "total": 866.8103760549129, "count": 44539, "is_parallel": true, "self": 23.335727580564708, "children": { "UnityEnvironment._generate_step_input": { "total": 16.370495459745143, "count": 44539, "is_parallel": true, "self": 16.370495459745143 }, "communicator.exchange": { "total": 752.8083490887766, "count": 44539, "is_parallel": true, "self": 752.8083490887766 }, "steps_from_proto": { "total": 74.29580392582648, "count": 44539, "is_parallel": true, "self": 15.610935690858241, "children": { "_process_rank_one_or_two_observation": { "total": 58.684868234968235, "count": 356312, "is_parallel": true, "self": 58.684868234968235 } } } } } } } } } } }, "trainer_advance": { "total": 455.13096195315666, "count": 44540, "self": 1.8208620301757037, "children": { "process_trajectory": { "total": 86.41271897398292, "count": 44540, "self": 86.15479847298229, "children": { "RLTrainer._checkpoint": { "total": 0.25792050100062625, "count": 2, "self": 0.25792050100062625 } } }, "_update_policy": { "total": 366.89738094899803, "count": 322, "self": 202.94853052493454, "children": { "TorchPPOOptimizer.update": { "total": 163.9488504240635, "count": 15933, "self": 163.9488504240635 } } } } } } }, "trainer_threads": { "total": 1.1699994502123445e-06, "count": 1, "self": 1.1699994502123445e-06 }, "TrainerController._save_models": { "total": 0.10178152599837631, "count": 1, "self": 0.0024809429996821564, "children": { "RLTrainer._checkpoint": { "total": 0.09930058299869415, "count": 1, "self": 0.09930058299869415 } } } } } } }