{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7285130620002747, "min": 0.7285130620002747, "max": 1.3428857326507568, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 21727.173828125, "min": 21727.173828125, "max": 40737.78125, "count": 33 }, "Pyramids.Step.mean": { "value": 989902.0, "min": 29952.0, "max": 989902.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989902.0, "min": 29952.0, "max": 989902.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2144729048013687, "min": -0.13779912889003754, "max": 0.24664872884750366, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 54.47611618041992, "min": -33.209590911865234, "max": 63.88201904296875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.48129403591156006, "min": -0.48129403591156006, "max": 0.4290876090526581, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -122.24868774414062, "min": -122.24868774414062, "max": 101.69376373291016, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06915227169658812, "min": 0.06485435272992852, "max": 0.07248497862745026, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9681318037522336, "min": 0.5036409776833446, "max": 1.0562414092402084, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.047634738351101664, "min": 0.0001355556308406222, "max": 0.05362570525695837, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.6668863369154233, "min": 0.0017622232009280887, "max": 0.7507598735974171, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 8.977147435128566e-06, "min": 8.977147435128566e-06, "max": 0.00034434240161645714, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00012568006409179993, "min": 0.00012568006409179993, "max": 0.0036595708544084004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256487142857143, "min": 0.10256487142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359082, "min": 1.3886848, "max": 2.3592186, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026623065571428566, "min": 0.00026623065571428566, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003727229179999999, "min": 0.003727229179999999, "max": 0.10458460083999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011957399547100067, "min": 0.011434567160904408, "max": 0.5550337433815002, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16740359365940094, "min": 0.16008393466472626, "max": 3.8852362632751465, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 644.8444444444444, "min": 572.0384615384615, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29018.0, "min": 15984.0, "max": 32917.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.910564410355356, "min": -1.0000000521540642, "max": 1.0432153556209345, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 40.97539846599102, "min": -32.000001668930054, "max": 54.24719849228859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.910564410355356, "min": -1.0000000521540642, "max": 1.0432153556209345, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 40.97539846599102, "min": -32.000001668930054, "max": 54.24719849228859, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07881952961066013, "min": 0.07029861580499877, "max": 11.176115886308253, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.546878832479706, "min": 3.546878832479706, "max": 178.81785418093204, "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": "1712281273", "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": "1712283332" }, "total": 2058.684886752, "count": 1, "self": 0.6425813969995033, "children": { "run_training.setup": { "total": 0.05237031800004388, "count": 1, "self": 0.05237031800004388 }, "TrainerController.start_learning": { "total": 2057.989935037, "count": 1, "self": 1.4193797350394561, "children": { "TrainerController._reset_env": { "total": 3.5401856879999514, "count": 1, "self": 3.5401856879999514 }, "TrainerController.advance": { "total": 2052.892088131961, "count": 63299, "self": 1.4384489299477536, "children": { "env_step": { "total": 1418.656423797015, "count": 63299, "self": 1282.99387655502, "children": { "SubprocessEnvManager._take_step": { "total": 134.77631047396972, "count": 63299, "self": 4.659826753982429, "children": { "TorchPolicy.evaluate": { "total": 130.1164837199873, "count": 62580, "self": 130.1164837199873 } } }, "workers": { "total": 0.8862367680250145, "count": 63299, "self": 0.0, "children": { "worker_root": { "total": 2053.199921089, "count": 63299, "is_parallel": true, "self": 892.5979913679746, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005627552999953878, "count": 1, "is_parallel": true, "self": 0.004181867999932365, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014456850000215127, "count": 8, "is_parallel": true, "self": 0.0014456850000215127 } } }, "UnityEnvironment.step": { "total": 0.04844340199997532, "count": 1, "is_parallel": true, "self": 0.0006532019999667682, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004706429999714601, "count": 1, "is_parallel": true, "self": 0.0004706429999714601 }, "communicator.exchange": { "total": 0.0456542829999762, "count": 1, "is_parallel": true, "self": 0.0456542829999762 }, "steps_from_proto": { "total": 0.00166527400006089, "count": 1, "is_parallel": true, "self": 0.00036683900009393255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012984349999669575, "count": 8, "is_parallel": true, "self": 0.0012984349999669575 } } } } } } }, "UnityEnvironment.step": { "total": 1160.6019297210253, "count": 63298, "is_parallel": true, "self": 34.64191122903617, "children": { "UnityEnvironment._generate_step_input": { "total": 23.578938466018258, "count": 63298, "is_parallel": true, "self": 23.578938466018258 }, "communicator.exchange": { "total": 1003.4180351280205, "count": 63298, "is_parallel": true, "self": 1003.4180351280205 }, "steps_from_proto": { "total": 98.96304489795045, "count": 63298, "is_parallel": true, "self": 19.8966114580478, "children": { "_process_rank_one_or_two_observation": { "total": 79.06643343990265, "count": 506384, "is_parallel": true, "self": 79.06643343990265 } } } } } } } } } } }, "trainer_advance": { "total": 632.7972154049984, "count": 63299, "self": 2.694936983932621, "children": { "process_trajectory": { "total": 124.98230429606883, "count": 63299, "self": 124.67452967806912, "children": { "RLTrainer._checkpoint": { "total": 0.30777461799971206, "count": 2, "self": 0.30777461799971206 } } }, "_update_policy": { "total": 505.11997412499693, "count": 441, "self": 295.6290800909992, "children": { "TorchPPOOptimizer.update": { "total": 209.49089403399773, "count": 22830, "self": 209.49089403399773 } } } } } } }, "trainer_threads": { "total": 1.4140000530460384e-06, "count": 1, "self": 1.4140000530460384e-06 }, "TrainerController._save_models": { "total": 0.13828006799985815, "count": 1, "self": 0.002243861999886576, "children": { "RLTrainer._checkpoint": { "total": 0.13603620599997157, "count": 1, "self": 0.13603620599997157 } } } } } } }