{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32002681493759155, "min": 0.308307945728302, "max": 1.4006235599517822, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9754.4169921875, "min": 9209.775390625, "max": 42489.31640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29890.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29890.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6187016367912292, "min": -0.08682476729154587, "max": 0.6187016367912292, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 175.09255981445312, "min": -21.098419189453125, "max": 175.09255981445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03823251649737358, "min": -0.013099354691803455, "max": 0.43473541736602783, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.819802284240723, "min": -3.6809186935424805, "max": 103.03229522705078, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06990852425570351, "min": 0.0648973197765102, "max": 0.07441313110645313, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0486278638355526, "min": 0.520891917745172, "max": 1.0782243527355606, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017000644672715285, "min": 0.0019498057577543983, "max": 0.01733061000617535, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2550096700907293, "min": 0.025347474850807176, "max": 0.2550096700907293, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.546897484400001e-06, "min": 7.546897484400001e-06, "max": 0.0002952355730167143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011320346226600001, "min": 0.00011320346226600001, "max": 0.003633325988891399, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251560000000001, "min": 0.10251560000000001, "max": 0.1984118571428571, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377340000000002, "min": 1.3888829999999999, "max": 2.6111086000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026130844000000006, "min": 0.00026130844000000006, "max": 0.009841344528571428, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003919626600000001, "min": 0.003919626600000001, "max": 0.12112974914000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010051882825791836, "min": 0.010051882825791836, "max": 0.4846421778202057, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15077824890613556, "min": 0.14303304255008698, "max": 3.3924951553344727, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.22105263157897, "min": 299.22105263157897, "max": 982.4333333333333, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28426.0, "min": 16561.0, "max": 33617.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6797199915898473, "min": -0.857470642117893, "max": 1.6797199915898473, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 159.5733992010355, "min": -28.22460174560547, "max": 159.5733992010355, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6797199915898473, "min": -0.857470642117893, "max": 1.6797199915898473, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 159.5733992010355, "min": -28.22460174560547, "max": 159.5733992010355, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03136997654219158, "min": 0.03136997654219158, "max": 9.870001710513058, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9801477715082, "min": 2.9801477715082, "max": 167.790029078722, "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": "1720462741", "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": "1720465121" }, "total": 2380.8161381229997, "count": 1, "self": 0.5281798270002582, "children": { "run_training.setup": { "total": 0.05678266899985829, "count": 1, "self": 0.05678266899985829 }, "TrainerController.start_learning": { "total": 2380.2311756269996, "count": 1, "self": 1.4995604969767555, "children": { "TrainerController._reset_env": { "total": 2.82333522800036, "count": 1, "self": 2.82333522800036 }, "TrainerController.advance": { "total": 2375.819174291022, "count": 63979, "self": 1.5727623058505742, "children": { "env_step": { "total": 1702.06913079803, "count": 63979, "self": 1555.5403817829324, "children": { "SubprocessEnvManager._take_step": { "total": 145.56907919505966, "count": 63979, "self": 5.037140449007893, "children": { "TorchPolicy.evaluate": { "total": 140.53193874605176, "count": 62552, "self": 140.53193874605176 } } }, "workers": { "total": 0.959669820038016, "count": 63979, "self": 0.0, "children": { "worker_root": { "total": 2374.5582352400543, "count": 63979, "is_parallel": true, "self": 951.6149676650948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020211499995639315, "count": 1, "is_parallel": true, "self": 0.0006020209989401337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014191290006237978, "count": 8, "is_parallel": true, "self": 0.0014191290006237978 } } }, "UnityEnvironment.step": { "total": 0.07655681000005643, "count": 1, "is_parallel": true, "self": 0.0006626680001318164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00042039399977511493, "count": 1, "is_parallel": true, "self": 0.00042039399977511493 }, "communicator.exchange": { "total": 0.07341984699996829, "count": 1, "is_parallel": true, "self": 0.07341984699996829 }, "steps_from_proto": { "total": 0.002053901000181213, "count": 1, "is_parallel": true, "self": 0.0003722069991454191, "children": { "_process_rank_one_or_two_observation": { "total": 0.001681694001035794, "count": 8, "is_parallel": true, "self": 0.001681694001035794 } } } } } } }, "UnityEnvironment.step": { "total": 1422.9432675749595, "count": 63978, "is_parallel": true, "self": 36.672151332844805, "children": { "UnityEnvironment._generate_step_input": { "total": 24.17241522507038, "count": 63978, "is_parallel": true, "self": 24.17241522507038 }, "communicator.exchange": { "total": 1257.8588582470688, "count": 63978, "is_parallel": true, "self": 1257.8588582470688 }, "steps_from_proto": { "total": 104.23984276997544, "count": 63978, "is_parallel": true, "self": 21.324798234888476, "children": { "_process_rank_one_or_two_observation": { "total": 82.91504453508696, "count": 511824, "is_parallel": true, "self": 82.91504453508696 } } } } } } } } } } }, "trainer_advance": { "total": 672.1772811871415, "count": 63979, "self": 2.991118616208496, "children": { "process_trajectory": { "total": 135.8312129859355, "count": 63979, "self": 135.61291930993502, "children": { "RLTrainer._checkpoint": { "total": 0.218293676000485, "count": 2, "self": 0.218293676000485 } } }, "_update_policy": { "total": 533.3549495849975, "count": 457, "self": 312.8315300799636, "children": { "TorchPPOOptimizer.update": { "total": 220.52341950503387, "count": 22779, "self": 220.52341950503387 } } } } } } }, "trainer_threads": { "total": 8.699998943484388e-07, "count": 1, "self": 8.699998943484388e-07 }, "TrainerController._save_models": { "total": 0.08910474100048305, "count": 1, "self": 0.001412012000400864, "children": { "RLTrainer._checkpoint": { "total": 0.08769272900008218, "count": 1, "self": 0.08769272900008218 } } } } } } }