{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29161450266838074, "min": 0.26832109689712524, "max": 1.4448745250701904, "count": 56 }, "Pyramids.Policy.Entropy.sum": { "value": 8692.4453125, "min": 8046.072265625, "max": 43831.71484375, "count": 56 }, "Pyramids.Step.mean": { "value": 1679902.0, "min": 29952.0, "max": 1679902.0, "count": 56 }, "Pyramids.Step.sum": { "value": 1679902.0, "min": 29952.0, "max": 1679902.0, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7371307015419006, "min": -0.09672346711158752, "max": 0.7979226112365723, "count": 56 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 217.45355224609375, "min": -23.31035614013672, "max": 234.58924865722656, "count": 56 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02280416339635849, "min": -0.009110200218856335, "max": 0.34660589694976807, "count": 56 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.727228164672852, "min": -2.3156561851501465, "max": 83.53202056884766, "count": 56 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06929605025634221, "min": 0.06526765752988424, "max": 0.0735187948817232, "count": 56 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9701447035887909, "min": 0.5087351455263213, "max": 1.102781923225848, "count": 56 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014207130402979749, "min": 0.0002094138638317064, "max": 0.016501869111033598, "count": 56 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1988998256417165, "min": 0.002722380229812183, "max": 0.24538141228064583, "count": 56 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0001334438983758619, "min": 0.0001334438983758619, "max": 0.00029838354339596195, "count": 56 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0018682145772620665, "min": 0.0018682145772620665, "max": 0.0038852456049181666, "count": 56 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14448128095238097, "min": 0.14448128095238097, "max": 0.19946118095238097, "count": 56 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0227379333333335, "min": 1.3962282666666668, "max": 2.6950818333333335, "count": 56 }, "Pyramids.Policy.Beta.mean": { "value": 0.004453679967142857, "min": 0.004453679967142857, "max": 0.009946171977142856, "count": 56 }, "Pyramids.Policy.Beta.sum": { "value": 0.06235151953999999, "min": 0.06235151953999999, "max": 0.12951867515, "count": 56 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005804836750030518, "min": 0.005547815002501011, "max": 0.40933331847190857, "count": 56 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08126771450042725, "min": 0.0776694118976593, "max": 2.865333318710327, "count": 56 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 249.71311475409837, "min": 240.1900826446281, "max": 999.0, "count": 56 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30465.0, "min": 15984.0, "max": 32648.0, "count": 56 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7502868754453347, "min": -1.0000000521540642, "max": 1.7527295010255985, "count": 56 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 213.53499880433083, "min": -31.996001660823822, "max": 213.83299912512302, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7502868754453347, "min": -1.0000000521540642, "max": 1.7527295010255985, "count": 56 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 213.53499880433083, "min": -31.996001660823822, "max": 213.83299912512302, "count": 56 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014921443852546842, "min": 0.014662963339714738, "max": 8.126681023277342, "count": 56 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8204161500107148, "min": 1.686240784067195, "max": 130.02689637243748, "count": 56 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 56 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1774003215", "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=PyramidsTraining --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": "1774007195" }, "total": 3980.1464101170004, "count": 1, "self": 0.41625770700011344, "children": { "run_training.setup": { "total": 0.03520064500003173, "count": 1, "self": 0.03520064500003173 }, "TrainerController.start_learning": { "total": 3979.694951765, "count": 1, "self": 2.316845138917415, "children": { "TrainerController._reset_env": { "total": 3.435058239, "count": 1, "self": 3.435058239 }, "TrainerController.advance": { "total": 3973.809470198083, "count": 108490, "self": 2.4656409260237524, "children": { "env_step": { "total": 2844.1607173239854, "count": 108490, "self": 2582.4004485938763, "children": { "SubprocessEnvManager._take_step": { "total": 260.3345160460326, "count": 108490, "self": 8.062287990032928, "children": { "TorchPolicy.evaluate": { "total": 252.27222805599968, "count": 105310, "self": 252.27222805599968 } } }, "workers": { "total": 1.4257526840765422, "count": 108489, "self": 0.0, "children": { "worker_root": { "total": 3968.560015425031, "count": 108489, "is_parallel": true, "self": 1588.4012289901093, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007264788000156841, "count": 1, "is_parallel": true, "self": 0.004998805000013817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022659830001430237, "count": 8, "is_parallel": true, "self": 0.0022659830001430237 } } }, "UnityEnvironment.step": { "total": 0.05688294800006588, "count": 1, "is_parallel": true, "self": 0.0005364270002701232, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048206199994638155, "count": 1, "is_parallel": true, "self": 0.00048206199994638155 }, "communicator.exchange": { "total": 0.05430029499984812, "count": 1, "is_parallel": true, "self": 0.05430029499984812 }, "steps_from_proto": { "total": 0.0015641640000012558, "count": 1, "is_parallel": true, "self": 0.00035776199956671917, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012064020004345366, "count": 8, "is_parallel": true, "self": 0.0012064020004345366 } } } } } } }, "UnityEnvironment.step": { "total": 2380.1587864349217, "count": 108488, "is_parallel": true, "self": 58.77171501287512, "children": { "UnityEnvironment._generate_step_input": { "total": 39.57980959893621, "count": 108488, "is_parallel": true, "self": 39.57980959893621 }, "communicator.exchange": { "total": 2096.553100965014, "count": 108488, "is_parallel": true, "self": 2096.553100965014 }, "steps_from_proto": { "total": 185.25416085809616, "count": 108488, "is_parallel": true, "self": 38.8669858294752, "children": { "_process_rank_one_or_two_observation": { "total": 146.38717502862096, "count": 867904, "is_parallel": true, "self": 146.38717502862096 } } } } } } } } } } }, "trainer_advance": { "total": 1127.1831119480742, "count": 108489, "self": 4.734776398998974, "children": { "process_trajectory": { "total": 215.01470632207815, "count": 108489, "self": 214.66923381607808, "children": { "RLTrainer._checkpoint": { "total": 0.3454725060000783, "count": 3, "self": 0.3454725060000783 } } }, "_update_policy": { "total": 907.433629226997, "count": 771, "self": 501.85991378000654, "children": { "TorchPPOOptimizer.update": { "total": 405.5737154469905, "count": 38421, "self": 405.5737154469905 } } } } } } }, "trainer_threads": { "total": 1.526999767520465e-06, "count": 1, "self": 1.526999767520465e-06 }, "TrainerController._save_models": { "total": 0.1335766619995411, "count": 1, "self": 0.0014462199997069547, "children": { "RLTrainer._checkpoint": { "total": 0.13213044199983415, "count": 1, "self": 0.13213044199983415 } } } } } } }