{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38231709599494934, "min": 0.38231709599494934, "max": 1.4944969415664673, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11292.1181640625, "min": 11292.1181640625, "max": 45337.05859375, "count": 33 }, "Pyramids.Step.mean": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989925.0, "min": 29952.0, "max": 989925.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6186416149139404, "min": -0.06953807920217514, "max": 0.6261042356491089, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.6942138671875, "min": -16.828214645385742, "max": 178.43971252441406, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005877800285816193, "min": -0.0035303542390465736, "max": 0.25761762261390686, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.669295310974121, "min": -0.9849688410758972, "max": 61.82822799682617, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07053150946063418, "min": 0.0644864332210827, "max": 0.07353129327748918, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9874411324488784, "min": 0.49912314937850083, "max": 1.0532045862540447, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014257595735738714, "min": 0.0011016902862592522, "max": 0.015586029324864484, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.199606340300342, "min": 0.007711832003814765, "max": 0.21820441054810277, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.0147045506257968e-05, "min": 1.0147045506257968e-05, "max": 0.0002951938852208976, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00014205863708761156, "min": 0.00014205863708761156, "max": 0.003639878184725173, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10338231629619143, "min": 0.10338231629619143, "max": 0.1983979612062863, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.44735242814668, "min": 1.3693890981169472, "max": 2.6132926660059472, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000347893397989523, "min": 0.000347893397989523, "max": 0.009839956324508, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.004870507571853322, "min": 0.004870507571853322, "max": 0.12134793733399406, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007071653846651316, "min": 0.007071653846651316, "max": 0.38067108392715454, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.0990031510591507, "min": 0.0990031510591507, "max": 2.6646976470947266, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 301.6831683168317, "min": 301.6831683168317, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30470.0, "min": 15984.0, "max": 32636.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6587009745659214, "min": -1.0000000521540642, "max": 1.6870449257365774, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 167.52879843115807, "min": -32.000001668930054, "max": 167.52879843115807, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6587009745659214, "min": -1.0000000521540642, "max": 1.6870449257365774, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 167.52879843115807, "min": -32.000001668930054, "max": 167.52879843115807, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02203766515609315, "min": 0.02203766515609315, "max": 7.524008542299271, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.225804180765408, "min": 2.0949891084019328, "max": 120.38413667678833, "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": "1709224060", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709226302" }, "total": 2241.47639622, "count": 1, "self": 0.7105202580000878, "children": { "run_training.setup": { "total": 0.04944692800017947, "count": 1, "self": 0.04944692800017947 }, "TrainerController.start_learning": { "total": 2240.7164290339997, "count": 1, "self": 1.3455406860248331, "children": { "TrainerController._reset_env": { "total": 3.371157657999902, "count": 1, "self": 3.371157657999902 }, "TrainerController.advance": { "total": 2235.8740682069756, "count": 64861, "self": 1.5258887910831618, "children": { "env_step": { "total": 1601.1954687489501, "count": 64861, "self": 1471.6833995939442, "children": { "SubprocessEnvManager._take_step": { "total": 128.6800177130708, "count": 64861, "self": 4.6115159430582935, "children": { "TorchPolicy.evaluate": { "total": 124.06850177001252, "count": 63149, "self": 124.06850177001252 } } }, "workers": { "total": 0.8320514419351639, "count": 64861, "self": 0.0, "children": { "worker_root": { "total": 2235.484465490114, "count": 64861, "is_parallel": true, "self": 880.3156610800738, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005353417000151239, "count": 1, "is_parallel": true, "self": 0.004001277000043046, "children": { "_process_rank_one_or_two_observation": { "total": 0.001352140000108193, "count": 8, "is_parallel": true, "self": 0.001352140000108193 } } }, "UnityEnvironment.step": { "total": 0.0491004239997892, "count": 1, "is_parallel": true, "self": 0.0006150679992060759, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004847800000788993, "count": 1, "is_parallel": true, "self": 0.0004847800000788993 }, "communicator.exchange": { "total": 0.04640720100042017, "count": 1, "is_parallel": true, "self": 0.04640720100042017 }, "steps_from_proto": { "total": 0.0015933750000840519, "count": 1, "is_parallel": true, "self": 0.0003471599998192687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012462150002647832, "count": 8, "is_parallel": true, "self": 0.0012462150002647832 } } } } } } }, "UnityEnvironment.step": { "total": 1355.1688044100401, "count": 64860, "is_parallel": true, "self": 36.060724112135176, "children": { "UnityEnvironment._generate_step_input": { "total": 24.53979809995417, "count": 64860, "is_parallel": true, "self": 24.53979809995417 }, "communicator.exchange": { "total": 1194.306809461972, "count": 64860, "is_parallel": true, "self": 1194.306809461972 }, "steps_from_proto": { "total": 100.26147273597871, "count": 64860, "is_parallel": true, "self": 19.81074685082058, "children": { "_process_rank_one_or_two_observation": { "total": 80.45072588515814, "count": 518880, "is_parallel": true, "self": 80.45072588515814 } } } } } } } } } } }, "trainer_advance": { "total": 633.1527106669423, "count": 64861, "self": 2.7284159519767854, "children": { "process_trajectory": { "total": 127.63635243096678, "count": 64861, "self": 127.400298198967, "children": { "RLTrainer._checkpoint": { "total": 0.2360542319997876, "count": 2, "self": 0.2360542319997876 } } }, "_update_policy": { "total": 502.78794228399875, "count": 458, "self": 293.0771406549975, "children": { "TorchPPOOptimizer.update": { "total": 209.71080162900125, "count": 23001, "self": 209.71080162900125 } } } } } } }, "trainer_threads": { "total": 1.3709995982935652e-06, "count": 1, "self": 1.3709995982935652e-06 }, "TrainerController._save_models": { "total": 0.1256611119997615, "count": 1, "self": 0.0019485909997456474, "children": { "RLTrainer._checkpoint": { "total": 0.12371252100001584, "count": 1, "self": 0.12371252100001584 } } } } } } }