{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4064662754535675, "min": 0.4017195403575897, "max": 1.442296028137207, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12141.9609375, "min": 12141.9609375, "max": 43753.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989996.0, "min": 29952.0, "max": 989996.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3491092622280121, "min": -0.10406745970249176, "max": 0.43275660276412964, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 92.51395416259766, "min": -25.080257415771484, "max": 116.84428405761719, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004166535101830959, "min": -0.009013254195451736, "max": 0.45860183238983154, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.104131817817688, "min": -2.3073930740356445, "max": 108.68863677978516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0679852888033363, "min": 0.06515967724374762, "max": 0.07119183655032894, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0197793320500446, "min": 0.4897881314284222, "max": 1.0332208417096933, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012537463655139114, "min": 0.0002068525116321086, "max": 0.014818031923968794, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1880619548270867, "min": 0.002482230139585303, "max": 0.2074524469355631, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468157510646668e-06, "min": 7.468157510646668e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011202236265970002, "min": 0.00011202236265970002, "max": 0.0035070425309859004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248935333333334, "min": 0.10248935333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373403, "min": 1.3886848, "max": 2.5690141, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002586863980000001, "min": 0.0002586863980000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038802959700000015, "min": 0.0038802959700000015, "max": 0.11692450859000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01746286079287529, "min": 0.016987264156341553, "max": 0.5054084658622742, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.26194292306900024, "min": 0.23782169818878174, "max": 3.5378592014312744, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 487.984375, "min": 430.7162162162162, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31231.0, "min": 15984.0, "max": 31968.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.230665598064661, "min": -1.0000000521540642, "max": 1.4099216005085289, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 78.7625982761383, "min": -31.996801659464836, "max": 104.33419843763113, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.230665598064661, "min": -1.0000000521540642, "max": 1.4099216005085289, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 78.7625982761383, "min": -31.996801659464836, "max": 104.33419843763113, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0886715158379161, "min": 0.07828882563665723, "max": 9.789739102125168, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.674977013626631, "min": 4.995954362733755, "max": 156.63582563400269, "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": "1720133112", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720135106" }, "total": 1993.6533737440004, "count": 1, "self": 0.324969688001147, "children": { "run_training.setup": { "total": 0.05588650499976211, "count": 1, "self": 0.05588650499976211 }, "TrainerController.start_learning": { "total": 1993.2725175509995, "count": 1, "self": 1.3259706880799058, "children": { "TrainerController._reset_env": { "total": 2.1439521739994234, "count": 1, "self": 2.1439521739994234 }, "TrainerController.advance": { "total": 1989.7082230239203, "count": 63498, "self": 1.2312032081581492, "children": { "env_step": { "total": 1347.5272236358342, "count": 63498, "self": 1223.436681439839, "children": { "SubprocessEnvManager._take_step": { "total": 123.23420442280258, "count": 63498, "self": 3.5521803587062095, "children": { "TorchPolicy.evaluate": { "total": 119.68202406409637, "count": 62553, "self": 119.68202406409637 } } }, "workers": { "total": 0.8563377731925357, "count": 63498, "self": 0.0, "children": { "worker_root": { "total": 1990.4499189669405, "count": 63498, "is_parallel": true, "self": 881.9011948608158, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023894870000731316, "count": 1, "is_parallel": true, "self": 0.0005747300001530675, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018147569999200641, "count": 8, "is_parallel": true, "self": 0.0018147569999200641 } } }, "UnityEnvironment.step": { "total": 0.04066331400008494, "count": 1, "is_parallel": true, "self": 0.0004081469996890519, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048226800026895944, "count": 1, "is_parallel": true, "self": 0.00048226800026895944 }, "communicator.exchange": { "total": 0.03877550099969085, "count": 1, "is_parallel": true, "self": 0.03877550099969085 }, "steps_from_proto": { "total": 0.0009973980004360783, "count": 1, "is_parallel": true, "self": 0.0002506419987184927, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007467560017175856, "count": 8, "is_parallel": true, "self": 0.0007467560017175856 } } } } } } }, "UnityEnvironment.step": { "total": 1108.5487241061246, "count": 63497, "is_parallel": true, "self": 42.20019129116099, "children": { "UnityEnvironment._generate_step_input": { "total": 26.387485024985835, "count": 63497, "is_parallel": true, "self": 26.387485024985835 }, "communicator.exchange": { "total": 931.4861125372181, "count": 63497, "is_parallel": true, "self": 931.4861125372181 }, "steps_from_proto": { "total": 108.47493525275968, "count": 63497, "is_parallel": true, "self": 23.547075291473448, "children": { "_process_rank_one_or_two_observation": { "total": 84.92785996128623, "count": 507976, "is_parallel": true, "self": 84.92785996128623 } } } } } } } } } } }, "trainer_advance": { "total": 640.949796179928, "count": 63498, "self": 2.540892343295127, "children": { "process_trajectory": { "total": 107.00191914164407, "count": 63498, "self": 106.80748049464364, "children": { "RLTrainer._checkpoint": { "total": 0.19443864700042468, "count": 2, "self": 0.19443864700042468 } } }, "_update_policy": { "total": 531.4069846949888, "count": 446, "self": 281.2913117101343, "children": { "TorchPPOOptimizer.update": { "total": 250.11567298485443, "count": 22821, "self": 250.11567298485443 } } } } } } }, "trainer_threads": { "total": 8.520000847056508e-07, "count": 1, "self": 8.520000847056508e-07 }, "TrainerController._save_models": { "total": 0.09437081299984129, "count": 1, "self": 0.00219305899918254, "children": { "RLTrainer._checkpoint": { "total": 0.09217775400065875, "count": 1, "self": 0.09217775400065875 } } } } } } }