{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5706483125686646, "min": 0.5444009304046631, "max": 1.4573984146118164, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17320.318359375, "min": 16192.662109375, "max": 44211.63671875, "count": 33 }, "Pyramids.Step.mean": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989927.0, "min": 29952.0, "max": 989927.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5362973213195801, "min": -0.09463559836149216, "max": 0.5362973213195801, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 145.87286376953125, "min": -22.807178497314453, "max": 145.87286376953125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.028460519388318062, "min": 0.004660688806325197, "max": 0.4314636290073395, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.7412614822387695, "min": 1.267707347869873, "max": 102.25688171386719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06730013438996127, "min": 0.06581899643771313, "max": 0.07500798211490879, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9422018814594578, "min": 0.4711803591071866, "max": 1.0535125777606997, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016224412030278877, "min": 9.905520426406784e-05, "max": 0.01670753930882152, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2271417684239043, "min": 0.0013867728596969498, "max": 0.2506130896323228, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.306983278657139e-06, "min": 7.306983278657139e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010229776590119995, "min": 0.00010229776590119995, "max": 0.0033832694722436, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243562857142859, "min": 0.10243562857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4340988000000001, "min": 1.3691136000000002, "max": 2.5277564000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025331929428571424, "min": 0.00025331929428571424, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003546470119999999, "min": 0.003546470119999999, "max": 0.11280286435999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010624746792018414, "min": 0.010624746792018414, "max": 0.6782323122024536, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14874646067619324, "min": 0.14874646067619324, "max": 4.747626304626465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 338.71084337349396, "min": 338.71084337349396, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28113.0, "min": 15984.0, "max": 34210.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5889734717377697, "min": -1.0000000521540642, "max": 1.5889734717377697, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 131.8847981542349, "min": -32.000001668930054, "max": 131.8847981542349, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5889734717377697, "min": -1.0000000521540642, "max": 1.5889734717377697, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 131.8847981542349, "min": -32.000001668930054, "max": 131.8847981542349, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0372863531271164, "min": 0.0372863531271164, "max": 13.966461382806301, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0947673095506616, "min": 3.0947673095506616, "max": 223.46338212490082, "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": "1740850295", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740853602" }, "total": 3306.586252864, "count": 1, "self": 0.5918194349997066, "children": { "run_training.setup": { "total": 0.03301063999970211, "count": 1, "self": 0.03301063999970211 }, "TrainerController.start_learning": { "total": 3305.9614227890006, "count": 1, "self": 2.282220172036432, "children": { "TrainerController._reset_env": { "total": 3.369369223000831, "count": 1, "self": 3.369369223000831 }, "TrainerController.advance": { "total": 3300.2178172829645, "count": 63628, "self": 2.5935067820064432, "children": { "env_step": { "total": 2168.498758719974, "count": 63628, "self": 1993.7246742767775, "children": { "SubprocessEnvManager._take_step": { "total": 173.38077121714286, "count": 63628, "self": 7.5683555160712785, "children": { "TorchPolicy.evaluate": { "total": 165.8124157010716, "count": 62556, "self": 165.8124157010716 } } }, "workers": { "total": 1.3933132260535785, "count": 63628, "self": 0.0, "children": { "worker_root": { "total": 3298.189052672222, "count": 63628, "is_parallel": true, "self": 1481.1402824790985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003959271999519842, "count": 1, "is_parallel": true, "self": 0.0013506019986380124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026086700008818298, "count": 8, "is_parallel": true, "self": 0.0026086700008818298 } } }, "UnityEnvironment.step": { "total": 0.1118370429994684, "count": 1, "is_parallel": true, "self": 0.000713412999175489, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005124150002302486, "count": 1, "is_parallel": true, "self": 0.0005124150002302486 }, "communicator.exchange": { "total": 0.10869726199962315, "count": 1, "is_parallel": true, "self": 0.10869726199962315 }, "steps_from_proto": { "total": 0.0019139530004395056, "count": 1, "is_parallel": true, "self": 0.00041166200117004337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015022909992694622, "count": 8, "is_parallel": true, "self": 0.0015022909992694622 } } } } } } }, "UnityEnvironment.step": { "total": 1817.0487701931233, "count": 63627, "is_parallel": true, "self": 45.56477164102307, "children": { "UnityEnvironment._generate_step_input": { "total": 31.810335540129927, "count": 63627, "is_parallel": true, "self": 31.810335540129927 }, "communicator.exchange": { "total": 1611.3633682679229, "count": 63627, "is_parallel": true, "self": 1611.3633682679229 }, "steps_from_proto": { "total": 128.3102947440475, "count": 63627, "is_parallel": true, "self": 27.81279490903944, "children": { "_process_rank_one_or_two_observation": { "total": 100.49749983500806, "count": 509016, "is_parallel": true, "self": 100.49749983500806 } } } } } } } } } } }, "trainer_advance": { "total": 1129.125551780984, "count": 63628, "self": 4.5302122267321465, "children": { "process_trajectory": { "total": 167.48792157827847, "count": 63628, "self": 167.27769615327816, "children": { "RLTrainer._checkpoint": { "total": 0.21022542500031705, "count": 2, "self": 0.21022542500031705 } } }, "_update_policy": { "total": 957.1074179759735, "count": 446, "self": 369.68338884195146, "children": { "TorchPPOOptimizer.update": { "total": 587.424029134022, "count": 22875, "self": 587.424029134022 } } } } } } }, "trainer_threads": { "total": 1.471998984925449e-06, "count": 1, "self": 1.471998984925449e-06 }, "TrainerController._save_models": { "total": 0.09201463899989903, "count": 1, "self": 0.0023882440000306815, "children": { "RLTrainer._checkpoint": { "total": 0.08962639499986835, "count": 1, "self": 0.08962639499986835 } } } } } } }