{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3381549119949341, "min": 0.30663561820983887, "max": 1.5821905136108398, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3489.7587890625, "min": 2992.763671875, "max": 16201.630859375, "count": 100 }, "Pyramids.Step.mean": { "value": 999995.0, "min": 9984.0, "max": 999995.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999995.0, "min": 9984.0, "max": 999995.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.31659725308418274, "min": -0.10878587514162064, "max": 0.4156027138233185, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 27.860557556152344, "min": -8.81165599822998, "max": 36.40038299560547, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00742553174495697, "min": -0.011789517477154732, "max": 0.4911734163761139, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6534467935562134, "min": -1.049267053604126, "max": 39.7850456237793, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07191944510753577, "min": 0.06179592022672296, "max": 0.07575078563725886, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.35959722553767887, "min": 0.13375348658448127, "max": 0.37406112408886355, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01577414447092451, "min": 9.62944506821057e-05, "max": 0.034981400970484654, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07887072235462256, "min": 0.0003851778027284228, "max": 0.07887072235462256, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.7190994270000035e-06, "min": 1.7190994270000035e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 8.595497135000017e-06, "min": 8.595497135000017e-06, "max": 0.0013880433373188999, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.100573, "min": 0.100573, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.502865, "min": 0.39319040000000005, "max": 0.9626811000000001, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.724270000000013e-05, "min": 6.724270000000013e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003362135000000007, "min": 0.0003362135000000007, "max": 0.04627184189, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012550015933811665, "min": 0.012550015933811665, "max": 1.0322835445404053, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06275007873773575, "min": 0.050218287855386734, "max": 2.0645670890808105, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 526.6818181818181, "min": 412.14285714285717, "max": 999.0, "count": 98 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 11587.0, "min": 1747.0, "max": 15984.0, "count": 98 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2004908739843152, "min": -1.0000000521540642, "max": 1.55754542960362, "count": 98 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 26.410799227654934, "min": -16.000000834465027, "max": 34.26599945127964, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2004908739843152, "min": -1.0000000521540642, "max": 1.55754542960362, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 26.410799227654934, "min": -16.000000834465027, "max": 34.26599945127964, "count": 98 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07074800053272735, "min": 0.05968590072838457, "max": 11.421275632455945, "count": 98 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5564560117200017, "min": 0.921070221462287, "max": 182.74041011929512, "count": 98 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685719254", "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 --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": "1685721437" }, "total": 2183.3714082740007, "count": 1, "self": 0.4751683000013145, "children": { "run_training.setup": { "total": 0.04123878199970932, "count": 1, "self": 0.04123878199970932 }, "TrainerController.start_learning": { "total": 2182.8550011919997, "count": 1, "self": 1.5765450789531315, "children": { "TrainerController._reset_env": { "total": 3.8741668029997527, "count": 1, "self": 3.8741668029997527 }, "TrainerController.advance": { "total": 2177.310387506047, "count": 63590, "self": 1.5387525799415016, "children": { "env_step": { "total": 1518.6369186990096, "count": 63590, "self": 1397.8130169001533, "children": { "SubprocessEnvManager._take_step": { "total": 119.8773790360101, "count": 63590, "self": 5.202901189084514, "children": { "TorchPolicy.evaluate": { "total": 114.67447784692558, "count": 62566, "self": 114.67447784692558 } } }, "workers": { "total": 0.9465227628461435, "count": 63590, "self": 0.0, "children": { "worker_root": { "total": 2177.572440894064, "count": 63590, "is_parallel": true, "self": 903.981175387964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017845309994299896, "count": 1, "is_parallel": true, "self": 0.0005415780005932902, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012429529988366994, "count": 8, "is_parallel": true, "self": 0.0012429529988366994 } } }, "UnityEnvironment.step": { "total": 0.050577883000187285, "count": 1, "is_parallel": true, "self": 0.000659770000311255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005537799997910042, "count": 1, "is_parallel": true, "self": 0.0005537799997910042 }, "communicator.exchange": { "total": 0.0473261460001595, "count": 1, "is_parallel": true, "self": 0.0473261460001595 }, "steps_from_proto": { "total": 0.0020381869999255287, "count": 1, "is_parallel": true, "self": 0.000408209999477549, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016299770004479797, "count": 8, "is_parallel": true, "self": 0.0016299770004479797 } } } } } } }, "UnityEnvironment.step": { "total": 1273.5912655061002, "count": 63589, "is_parallel": true, "self": 34.69814961594693, "children": { "UnityEnvironment._generate_step_input": { "total": 25.138212346057117, "count": 63589, "is_parallel": true, "self": 25.138212346057117 }, "communicator.exchange": { "total": 1101.8114663370807, "count": 63589, "is_parallel": true, "self": 1101.8114663370807 }, "steps_from_proto": { "total": 111.94343720701545, "count": 63589, "is_parallel": true, "self": 22.796880033839443, "children": { "_process_rank_one_or_two_observation": { "total": 89.146557173176, "count": 508712, "is_parallel": true, "self": 89.146557173176 } } } } } } } } } } }, "trainer_advance": { "total": 657.1347162270959, "count": 63590, "self": 2.9379905161422357, "children": { "process_trajectory": { "total": 116.4404291059509, "count": 63590, "self": 116.20810830795108, "children": { "RLTrainer._checkpoint": { "total": 0.23232079799981875, "count": 2, "self": 0.23232079799981875 } } }, "_update_policy": { "total": 537.7562966050027, "count": 452, "self": 348.80814536894013, "children": { "TorchPPOOptimizer.update": { "total": 188.94815123606259, "count": 22719, "self": 188.94815123606259 } } } } } } }, "trainer_threads": { "total": 1.0799994925037026e-06, "count": 1, "self": 1.0799994925037026e-06 }, "TrainerController._save_models": { "total": 0.09390072400037752, "count": 1, "self": 0.0013355890005186666, "children": { "RLTrainer._checkpoint": { "total": 0.09256513499985886, "count": 1, "self": 0.09256513499985886 } } } } } } }