{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5382451415061951, "min": 0.4699043929576874, "max": 1.5895313024520874, "count": 90 }, "Pyramids.Policy.Entropy.sum": { "value": 5304.9443359375, "min": 4744.15478515625, "max": 16276.80078125, "count": 90 }, "Pyramids.Step.mean": { "value": 899900.0, "min": 9984.0, "max": 899900.0, "count": 90 }, "Pyramids.Step.sum": { "value": 899900.0, "min": 9984.0, "max": 899900.0, "count": 90 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3402210474014282, "min": -0.09598982334136963, "max": 0.3596717417240143, "count": 90 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 29.939453125, "min": -7.77517557144165, "max": 32.37045669555664, "count": 90 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04390262812376022, "min": 0.0006706297281198204, "max": 0.41171517968177795, "count": 90 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.863431215286255, "min": 0.05499163642525673, "max": 33.34893035888672, "count": 90 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0711246652683864, "min": 0.06088816036935896, "max": 0.07885641973196328, "count": 90 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.355623326341932, "min": 0.13404133576356497, "max": 0.3839132064992252, "count": 90 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015882654131079713, "min": 7.877204982352506e-05, "max": 0.015882654131079713, "count": 90 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.07941327065539856, "min": 0.0003938602491176253, "max": 0.07941327065539856, "count": 90 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5905661365111122e-06, "min": 1.5905661365111122e-06, "max": 0.0002979520006826667, "count": 90 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.952830682555561e-06, "min": 7.952830682555561e-06, "max": 0.0013418060527313333, "count": 90 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10053015555555556, "min": 0.10053015555555556, "max": 0.19931733333333335, "count": 90 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5026507777777778, "min": 0.387968, "max": 0.9472686666666666, "count": 90 }, "Pyramids.Policy.Beta.mean": { "value": 6.296254000000005e-05, "min": 6.296254000000005e-05, "max": 0.009931801600000002, "count": 90 }, "Pyramids.Policy.Beta.sum": { "value": 0.0003148127000000002, "min": 0.0003148127000000002, "max": 0.0447321398, "count": 90 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01634393073618412, "min": 0.015565944835543633, "max": 0.7130684852600098, "count": 90 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08171965181827545, "min": 0.06226377934217453, "max": 1.4261369705200195, "count": 90 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 90 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 470.5217391304348, "min": 470.1904761904762, "max": 999.0, "count": 87 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 10822.0, "min": 999.0, "max": 16331.0, "count": 87 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3554956333144852, "min": -1.0000000521540642, "max": 1.4332545284520497, "count": 87 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 31.176399566233158, "min": -16.000000834465027, "max": 31.53159962594509, "count": 87 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3554956333144852, "min": -1.0000000521540642, "max": 1.4332545284520497, "count": 87 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 31.176399566233158, "min": -16.000000834465027, "max": 31.53159962594509, "count": 87 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07993838464481877, "min": 0.07993838464481877, "max": 7.421933939680457, "count": 87 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8385828468308318, "min": 0.8453424647450447, "max": 118.75094303488731, "count": 87 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1768633213", "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=PyramidsTraining3 --no-graphics", "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": "1768635017" }, "total": 1803.9394822232425, "count": 1, "self": 0.5785532966256142, "children": { "run_training.setup": { "total": 0.0617782287299633, "count": 1, "self": 0.0617782287299633 }, "TrainerController.start_learning": { "total": 1803.299150697887, "count": 1, "self": 0.6689807325601578, "children": { "TrainerController._reset_env": { "total": 3.833338249474764, "count": 1, "self": 3.833338249474764 }, "TrainerController.advance": { "total": 1798.5120954178274, "count": 56959, "self": 0.6877344958484173, "children": { "env_step": { "total": 1226.179904911667, "count": 56959, "self": 1142.1497384905815, "children": { "SubprocessEnvManager._take_step": { "total": 83.59406845271587, "count": 56959, "self": 2.3246328830718994, "children": { "TorchPolicy.evaluate": { "total": 81.26943556964397, "count": 56303, "self": 81.26943556964397 } } }, "workers": { "total": 0.43609796836972237, "count": 56959, "self": 0.0, "children": { "worker_root": { "total": 1801.0042517594993, "count": 56959, "is_parallel": true, "self": 729.0773673132062, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028846152126789093, "count": 1, "is_parallel": true, "self": 0.0008390657603740692, "children": { "_process_rank_one_or_two_observation": { "total": 0.00204554945230484, "count": 8, "is_parallel": true, "self": 0.00204554945230484 } } }, "UnityEnvironment.step": { "total": 0.04443683475255966, "count": 1, "is_parallel": true, "self": 0.0005918778479099274, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000521976500749588, "count": 1, "is_parallel": true, "self": 0.000521976500749588 }, "communicator.exchange": { "total": 0.04157690703868866, "count": 1, "is_parallel": true, "self": 0.04157690703868866 }, "steps_from_proto": { "total": 0.0017460733652114868, "count": 1, "is_parallel": true, "self": 0.00036179274320602417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013842806220054626, "count": 8, "is_parallel": true, "self": 0.0013842806220054626 } } } } } } }, "UnityEnvironment.step": { "total": 1071.9268844462931, "count": 56958, "is_parallel": true, "self": 31.503557574003935, "children": { "UnityEnvironment._generate_step_input": { "total": 22.295599069446325, "count": 56958, "is_parallel": true, "self": 22.295599069446325 }, "communicator.exchange": { "total": 932.8818535469472, "count": 56958, "is_parallel": true, "self": 932.8818535469472 }, "steps_from_proto": { "total": 85.24587425589561, "count": 56958, "is_parallel": true, "self": 15.251986850053072, "children": { "_process_rank_one_or_two_observation": { "total": 69.99388740584254, "count": 455664, "is_parallel": true, "self": 69.99388740584254 } } } } } } } } } } }, "trainer_advance": { "total": 571.6444560103118, "count": 56959, "self": 1.4138935543596745, "children": { "process_trajectory": { "total": 84.25038577988744, "count": 56959, "self": 83.95630147308111, "children": { "RLTrainer._checkpoint": { "total": 0.2940843068063259, "count": 1, "self": 0.2940843068063259 } } }, "_update_policy": { "total": 485.98017667606473, "count": 403, "self": 241.60718811303377, "children": { "TorchPPOOptimizer.update": { "total": 244.37298856303096, "count": 20511, "self": 244.37298856303096 } } } } } } }, "trainer_threads": { "total": 1.3932585716247559e-06, "count": 1, "self": 1.3932585716247559e-06 }, "TrainerController._save_models": { "total": 0.28473490476608276, "count": 1, "self": 0.0339621976017952, "children": { "RLTrainer._checkpoint": { "total": 0.25077270716428757, "count": 1, "self": 0.25077270716428757 } } } } } } }