{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4712701439857483, "min": 0.4712701439857483, "max": 1.4820386171340942, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13987.2978515625, "min": 13987.2978515625, "max": 44959.125, "count": 33 }, "Pyramids.Step.mean": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989878.0, "min": 29952.0, "max": 989878.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42283549904823303, "min": -0.10243896394968033, "max": 0.4617113173007965, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.31991577148438, "min": -24.585351943969727, "max": 123.73863220214844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.30384156107902527, "min": -0.052059877663850784, "max": 0.37808048725128174, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 81.42953491210938, "min": -13.795867919921875, "max": 99.81324768066406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06892085495859473, "min": 0.06610821029834132, "max": 0.07188616501692725, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9648919694203263, "min": 0.48992745796400494, "max": 1.0482212933032617, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019323462528908358, "min": 0.00018554448067320694, "max": 0.02402961155910614, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.27052847540471703, "min": 0.0022265337680784834, "max": 0.36044417338659207, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.421840383228569e-06, "min": 7.421840383228569e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010390576536519996, "min": 0.00010390576536519996, "max": 0.0032570649143118, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247391428571428, "min": 0.10247391428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346348, "min": 1.3691136000000002, "max": 2.4856882000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025714403714285704, "min": 0.00025714403714285704, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003600016519999999, "min": 0.003600016519999999, "max": 0.10860025118, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007577762473374605, "min": 0.00749658839777112, "max": 0.3398768901824951, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10608867555856705, "min": 0.10495223850011826, "max": 2.379138231277466, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 432.24, "min": 406.4054054054054, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32418.0, "min": 15984.0, "max": 33659.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.354367977976799, "min": -1.0000000521540642, "max": 1.4313783512727634, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 101.57759834825993, "min": -32.000001668930054, "max": 105.9219979941845, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.354367977976799, "min": -1.0000000521540642, "max": 1.4313783512727634, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 101.57759834825993, "min": -32.000001668930054, "max": 105.9219979941845, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03347987567462648, "min": 0.03297025881014683, "max": 6.348178546875715, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.510990675596986, "min": 2.1639718145597726, "max": 101.57085675001144, "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": "1722339076", "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722341234" }, "total": 2157.303466976, "count": 1, "self": 0.48800475699954404, "children": { "run_training.setup": { "total": 0.05365524600006211, "count": 1, "self": 0.05365524600006211 }, "TrainerController.start_learning": { "total": 2156.761806973, "count": 1, "self": 1.336872779965688, "children": { "TrainerController._reset_env": { "total": 2.141442739000013, "count": 1, "self": 2.141442739000013 }, "TrainerController.advance": { "total": 2153.198051818034, "count": 63605, "self": 1.4208591970063935, "children": { "env_step": { "total": 1515.4806609480736, "count": 63605, "self": 1383.5702232851588, "children": { "SubprocessEnvManager._take_step": { "total": 131.07994847598684, "count": 63605, "self": 4.8203369679520165, "children": { "TorchPolicy.evaluate": { "total": 126.25961150803482, "count": 62555, "self": 126.25961150803482 } } }, "workers": { "total": 0.8304891869279345, "count": 63605, "self": 0.0, "children": { "worker_root": { "total": 2151.7277252179406, "count": 63605, "is_parallel": true, "self": 886.7926002789827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002043433999915578, "count": 1, "is_parallel": true, "self": 0.0006393599996954435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014040740002201346, "count": 8, "is_parallel": true, "self": 0.0014040740002201346 } } }, "UnityEnvironment.step": { "total": 0.04757906399981948, "count": 1, "is_parallel": true, "self": 0.0006468060000770492, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043726599983529013, "count": 1, "is_parallel": true, "self": 0.00043726599983529013 }, "communicator.exchange": { "total": 0.04471061199978976, "count": 1, "is_parallel": true, "self": 0.04471061199978976 }, "steps_from_proto": { "total": 0.0017843800001173804, "count": 1, "is_parallel": true, "self": 0.0003517450002163969, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014326349999009835, "count": 8, "is_parallel": true, "self": 0.0014326349999009835 } } } } } } }, "UnityEnvironment.step": { "total": 1264.9351249389579, "count": 63604, "is_parallel": true, "self": 33.605364706956834, "children": { "UnityEnvironment._generate_step_input": { "total": 22.61490912401814, "count": 63604, "is_parallel": true, "self": 22.61490912401814 }, "communicator.exchange": { "total": 1113.6851054530093, "count": 63604, "is_parallel": true, "self": 1113.6851054530093 }, "steps_from_proto": { "total": 95.02974565497357, "count": 63604, "is_parallel": true, "self": 19.141902311760532, "children": { "_process_rank_one_or_two_observation": { "total": 75.88784334321304, "count": 508832, "is_parallel": true, "self": 75.88784334321304 } } } } } } } } } } }, "trainer_advance": { "total": 636.296531672954, "count": 63605, "self": 2.6893804830290264, "children": { "process_trajectory": { "total": 127.76348964592421, "count": 63605, "self": 127.57045956192383, "children": { "RLTrainer._checkpoint": { "total": 0.1930300840003838, "count": 2, "self": 0.1930300840003838 } } }, "_update_policy": { "total": 505.8436615440007, "count": 442, "self": 299.80770400099254, "children": { "TorchPPOOptimizer.update": { "total": 206.03595754300818, "count": 22824, "self": 206.03595754300818 } } } } } } }, "trainer_threads": { "total": 9.150003279501107e-07, "count": 1, "self": 9.150003279501107e-07 }, "TrainerController._save_models": { "total": 0.08543872100017325, "count": 1, "self": 0.0014520929998980137, "children": { "RLTrainer._checkpoint": { "total": 0.08398662800027523, "count": 1, "self": 0.08398662800027523 } } } } } } }