{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6854422092437744, "min": 0.6854422092437744, "max": 1.530413269996643, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20519.3984375, "min": 20519.3984375, "max": 46426.6171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09317854791879654, "min": -0.14085794985294342, "max": 0.14089640974998474, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 23.108280181884766, "min": -33.38333511352539, "max": 34.94231033325195, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01638438180088997, "min": 0.0034563359804451466, "max": 0.18125468492507935, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.063326835632324, "min": 0.8571712970733643, "max": 42.957359313964844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06798235708109585, "min": 0.06344787889387614, "max": 0.07135744118086775, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0197353562164377, "min": 0.4695197011032356, "max": 1.0197353562164377, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.007676091034824103, "min": 3.42937705489472e-05, "max": 0.008420066784787022, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11514136552236155, "min": 0.00044581901713631355, "max": 0.11788093498701832, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.508197497299997e-06, "min": 7.508197497299997e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011262296245949996, "min": 0.00011262296245949996, "max": 0.0033819344726886006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1025027, "min": 0.1025027, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5375405, "min": 1.3691136000000002, "max": 2.5273114000000008, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026001973000000007, "min": 0.00026001973000000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0039002959500000008, "min": 0.0039002959500000008, "max": 0.11275840886000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008498873561620712, "min": 0.008498873561620712, "max": 0.2964560091495514, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12748309969902039, "min": 0.11913242936134338, "max": 2.0751919746398926, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 767.1282051282051, "min": 712.175, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29918.0, "min": 15984.0, "max": 32181.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.2581435560415953, "min": -1.0000000521540642, "max": 0.4099435473863895, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 10.067598685622215, "min": -32.000001668930054, "max": 15.987798348069191, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.2581435560415953, "min": -1.0000000521540642, "max": 0.4099435473863895, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 10.067598685622215, "min": -32.000001668930054, "max": 15.987798348069191, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06777025429078211, "min": 0.06360156870505307, "max": 6.563605971634388, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.643039917340502, "min": 2.5440627482021227, "max": 105.01769554615021, "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": "1730454492", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1730456684" }, "total": 2191.806868478, "count": 1, "self": 0.6943519860001288, "children": { "run_training.setup": { "total": 0.05929490500011525, "count": 1, "self": 0.05929490500011525 }, "TrainerController.start_learning": { "total": 2191.053221587, "count": 1, "self": 1.408461138011262, "children": { "TrainerController._reset_env": { "total": 2.4186169800000243, "count": 1, "self": 2.4186169800000243 }, "TrainerController.advance": { "total": 2187.1391110479885, "count": 63159, "self": 1.4818728699406165, "children": { "env_step": { "total": 1476.5598903710495, "count": 63159, "self": 1318.4552605490846, "children": { "SubprocessEnvManager._take_step": { "total": 157.230744208975, "count": 63159, "self": 4.743012305939828, "children": { "TorchPolicy.evaluate": { "total": 152.48773190303518, "count": 62554, "self": 152.48773190303518 } } }, "workers": { "total": 0.8738856129898522, "count": 63159, "self": 0.0, "children": { "worker_root": { "total": 2185.8627173759874, "count": 63159, "is_parallel": true, "self": 987.238679166006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020921770001223194, "count": 1, "is_parallel": true, "self": 0.0006532299998980307, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014389470002242888, "count": 8, "is_parallel": true, "self": 0.0014389470002242888 } } }, "UnityEnvironment.step": { "total": 0.049834370000098716, "count": 1, "is_parallel": true, "self": 0.0006961530002627114, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046789999987595365, "count": 1, "is_parallel": true, "self": 0.00046789999987595365 }, "communicator.exchange": { "total": 0.046971153999948, "count": 1, "is_parallel": true, "self": 0.046971153999948 }, "steps_from_proto": { "total": 0.0016991630000120495, "count": 1, "is_parallel": true, "self": 0.00036070600026505417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013384569997469953, "count": 8, "is_parallel": true, "self": 0.0013384569997469953 } } } } } } }, "UnityEnvironment.step": { "total": 1198.6240382099813, "count": 63158, "is_parallel": true, "self": 34.39747256710098, "children": { "UnityEnvironment._generate_step_input": { "total": 22.97356503496826, "count": 63158, "is_parallel": true, "self": 22.97356503496826 }, "communicator.exchange": { "total": 1042.3158710379942, "count": 63158, "is_parallel": true, "self": 1042.3158710379942 }, "steps_from_proto": { "total": 98.93712956991794, "count": 63158, "is_parallel": true, "self": 20.33741738390836, "children": { "_process_rank_one_or_two_observation": { "total": 78.59971218600958, "count": 505264, "is_parallel": true, "self": 78.59971218600958 } } } } } } } } } } }, "trainer_advance": { "total": 709.0973478069986, "count": 63159, "self": 2.5114280899911137, "children": { "process_trajectory": { "total": 131.3474626840091, "count": 63159, "self": 131.10292807100882, "children": { "RLTrainer._checkpoint": { "total": 0.24453461300026902, "count": 2, "self": 0.24453461300026902 } } }, "_update_policy": { "total": 575.2384570329984, "count": 439, "self": 322.7364709079891, "children": { "TorchPPOOptimizer.update": { "total": 252.50198612500935, "count": 22845, "self": 252.50198612500935 } } } } } } }, "trainer_threads": { "total": 1.0439998732181266e-06, "count": 1, "self": 1.0439998732181266e-06 }, "TrainerController._save_models": { "total": 0.0870313770001303, "count": 1, "self": 0.001499715000136348, "children": { "RLTrainer._checkpoint": { "total": 0.08553166199999396, "count": 1, "self": 0.08553166199999396 } } } } } } }