{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5583076477050781, "min": 0.5401041507720947, "max": 1.5028109550476074, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16829.625, "min": 16116.70703125, "max": 45589.2734375, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4617052376270294, "min": -0.10633071511983871, "max": 0.4617052376270294, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 124.66041564941406, "min": -25.625701904296875, "max": 124.66041564941406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.93678879737854, "min": -0.6035766005516052, "max": 1.93678879737854, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 522.9329833984375, "min": -161.1549530029297, "max": 522.9329833984375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0664270811913801, "min": 0.06395238539747274, "max": 0.07150115735664274, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9299791366793215, "min": 0.48659962944950025, "max": 1.063720840718209, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.29116177310546243, "min": 0.0004502350735863746, "max": 0.29116177310546243, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 4.076264823476474, "min": 0.005765143436007245, "max": 4.076264823476474, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.661497446199999e-06, "min": 7.661497446199999e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010726096424679999, "min": 0.00010726096424679999, "max": 0.0035072771309077, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025538, "min": 0.1025538, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357532, "min": 1.3886848, "max": 2.5690923000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026512462000000006, "min": 0.00026512462000000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037117446800000006, "min": 0.0037117446800000006, "max": 0.11693232076999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01301711518317461, "min": 0.012592417187988758, "max": 0.4503241181373596, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1822396069765091, "min": 0.17629383504390717, "max": 3.152268886566162, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 409.69736842105266, "min": 409.69736842105266, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31137.0, "min": 15984.0, "max": 32725.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4628856927156448, "min": -1.0000000521540642, "max": 1.474008676474509, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 112.64219833910465, "min": -30.999801620841026, "max": 112.64219833910465, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4628856927156448, "min": -1.0000000521540642, "max": 1.474008676474509, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 112.64219833910465, "min": -30.999801620841026, "max": 112.64219833910465, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05553485349262158, "min": 0.05553485349262158, "max": 9.067114035598934, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.276183718931861, "min": 3.831101873278385, "max": 145.07382456958294, "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": "1706810483", "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": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706813135" }, "total": 2652.2042433260003, "count": 1, "self": 0.5601822759999777, "children": { "run_training.setup": { "total": 0.056556668000212085, "count": 1, "self": 0.056556668000212085 }, "TrainerController.start_learning": { "total": 2651.587504382, "count": 1, "self": 2.180839295950591, "children": { "TrainerController._reset_env": { "total": 3.430339496000215, "count": 1, "self": 3.430339496000215 }, "TrainerController.advance": { "total": 2645.8726152940494, "count": 63512, "self": 2.3511530220057466, "children": { "env_step": { "total": 1930.6745501379396, "count": 63512, "self": 1745.778249841006, "children": { "SubprocessEnvManager._take_step": { "total": 183.54614177189524, "count": 63512, "self": 6.380618960929951, "children": { "TorchPolicy.evaluate": { "total": 177.16552281096529, "count": 62566, "self": 177.16552281096529 } } }, "workers": { "total": 1.350158525038296, "count": 63512, "self": 0.0, "children": { "worker_root": { "total": 2645.266991238002, "count": 63512, "is_parallel": true, "self": 1057.5502830700061, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006173260999730701, "count": 1, "is_parallel": true, "self": 0.004383273999337689, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017899870003930118, "count": 8, "is_parallel": true, "self": 0.0017899870003930118 } } }, "UnityEnvironment.step": { "total": 0.11294232599993848, "count": 1, "is_parallel": true, "self": 0.0007456510002157302, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000591857000017626, "count": 1, "is_parallel": true, "self": 0.000591857000017626 }, "communicator.exchange": { "total": 0.1079907009998351, "count": 1, "is_parallel": true, "self": 0.1079907009998351 }, "steps_from_proto": { "total": 0.0036141169998700207, "count": 1, "is_parallel": true, "self": 0.0004595629993673356, "children": { "_process_rank_one_or_two_observation": { "total": 0.003154554000502685, "count": 8, "is_parallel": true, "self": 0.003154554000502685 } } } } } } }, "UnityEnvironment.step": { "total": 1587.7167081679959, "count": 63511, "is_parallel": true, "self": 44.97799124392304, "children": { "UnityEnvironment._generate_step_input": { "total": 30.51365260801458, "count": 63511, "is_parallel": true, "self": 30.51365260801458 }, "communicator.exchange": { "total": 1387.1508067020513, "count": 63511, "is_parallel": true, "self": 1387.1508067020513 }, "steps_from_proto": { "total": 125.07425761400691, "count": 63511, "is_parallel": true, "self": 26.538967677213805, "children": { "_process_rank_one_or_two_observation": { "total": 98.5352899367931, "count": 508088, "is_parallel": true, "self": 98.5352899367931 } } } } } } } } } } }, "trainer_advance": { "total": 712.8469121341041, "count": 63512, "self": 4.055480929015175, "children": { "process_trajectory": { "total": 144.44835541808743, "count": 63512, "self": 144.21622305508708, "children": { "RLTrainer._checkpoint": { "total": 0.23213236300034623, "count": 2, "self": 0.23213236300034623 } } }, "_update_policy": { "total": 564.3430757870015, "count": 447, "self": 326.28136604096926, "children": { "TorchPPOOptimizer.update": { "total": 238.0617097460322, "count": 22788, "self": 238.0617097460322 } } } } } } }, "trainer_threads": { "total": 1.002999852062203e-06, "count": 1, "self": 1.002999852062203e-06 }, "TrainerController._save_models": { "total": 0.10370929300006537, "count": 1, "self": 0.0015344460007327143, "children": { "RLTrainer._checkpoint": { "total": 0.10217484699933266, "count": 1, "self": 0.10217484699933266 } } } } } } }