{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.36324408650398254, "min": 0.36263951659202576, "max": 1.321979284286499, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10903.134765625, "min": 10821.1630859375, "max": 40103.5625, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.48503291606903076, "min": -0.26888924837112427, "max": 0.488682359457016, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 132.89901733398438, "min": -63.72675323486328, "max": 132.89901733398438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0131208011880517, "min": -0.08916240930557251, "max": 0.6215468049049377, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.595099449157715, "min": -24.163013458251953, "max": 147.3065948486328, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07063328150761868, "min": 0.06440895283407223, "max": 0.07746857166291621, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9888659411066614, "min": 0.4902344580017828, "max": 1.0608330956778909, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01458585456269092, "min": 0.0009905943323932377, "max": 0.018198541327553268, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2042019638776729, "min": 0.009222383719918134, "max": 0.23667086330533496, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.360704689321429e-06, "min": 7.360704689321429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010304986565050001, "min": 0.00010304986565050001, "max": 0.0036327052890983, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245353571428571, "min": 0.10245353571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343495, "min": 1.3691136000000002, "max": 2.6109017000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025510821785714285, "min": 0.00025510821785714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035715150499999997, "min": 0.0035715150499999997, "max": 0.12110907983000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013991400599479675, "min": 0.01376026589423418, "max": 0.8307117819786072, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19587960839271545, "min": 0.19264371693134308, "max": 5.8149824142456055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 388.64102564102564, "min": 376.0379746835443, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30314.0, "min": 15984.0, "max": 33693.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4831102354786334, "min": -1.0000000521540642, "max": 1.5226708573253849, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.68259836733341, "min": -32.000001668930054, "max": 120.2909977287054, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4831102354786334, "min": -1.0000000521540642, "max": 1.5226708573253849, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.68259836733341, "min": -32.000001668930054, "max": 120.2909977287054, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.058142706270117715, "min": 0.05765584434072177, "max": 17.78527825511992, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.535131089069182, "min": 3.854330282250885, "max": 284.5644520819187, "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": "1683287829", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683290154" }, "total": 2325.601415362, "count": 1, "self": 0.5388499529999535, "children": { "run_training.setup": { "total": 0.06192000999999436, "count": 1, "self": 0.06192000999999436 }, "TrainerController.start_learning": { "total": 2325.000645399, "count": 1, "self": 1.7763268789849462, "children": { "TrainerController._reset_env": { "total": 5.375168252999856, "count": 1, "self": 5.375168252999856 }, "TrainerController.advance": { "total": 2317.7536351380154, "count": 63693, "self": 1.7192676680028853, "children": { "env_step": { "total": 1649.9523592339963, "count": 63693, "self": 1519.3762891180625, "children": { "SubprocessEnvManager._take_step": { "total": 129.52106960588367, "count": 63693, "self": 5.544092186989019, "children": { "TorchPolicy.evaluate": { "total": 123.97697741889465, "count": 62548, "self": 123.97697741889465 } } }, "workers": { "total": 1.0550005100501494, "count": 63693, "self": 0.0, "children": { "worker_root": { "total": 2319.0847151349526, "count": 63693, "is_parallel": true, "self": 932.7682028139902, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026921520000087185, "count": 1, "is_parallel": true, "self": 0.0006244429996513645, "children": { "_process_rank_one_or_two_observation": { "total": 0.002067709000357354, "count": 8, "is_parallel": true, "self": 0.002067709000357354 } } }, "UnityEnvironment.step": { "total": 0.052274057000204266, "count": 1, "is_parallel": true, "self": 0.0006162810002479091, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005096029999549501, "count": 1, "is_parallel": true, "self": 0.0005096029999549501 }, "communicator.exchange": { "total": 0.04747238599998127, "count": 1, "is_parallel": true, "self": 0.04747238599998127 }, "steps_from_proto": { "total": 0.0036757870000201365, "count": 1, "is_parallel": true, "self": 0.002088824000338718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015869629996814183, "count": 8, "is_parallel": true, "self": 0.0015869629996814183 } } } } } } }, "UnityEnvironment.step": { "total": 1386.3165123209624, "count": 63692, "is_parallel": true, "self": 34.539465346095994, "children": { "UnityEnvironment._generate_step_input": { "total": 26.103750257000684, "count": 63692, "is_parallel": true, "self": 26.103750257000684 }, "communicator.exchange": { "total": 1212.9642471269021, "count": 63692, "is_parallel": true, "self": 1212.9642471269021 }, "steps_from_proto": { "total": 112.70904959096356, "count": 63692, "is_parallel": true, "self": 23.835787294889315, "children": { "_process_rank_one_or_two_observation": { "total": 88.87326229607424, "count": 509536, "is_parallel": true, "self": 88.87326229607424 } } } } } } } } } } }, "trainer_advance": { "total": 666.0820082360162, "count": 63693, "self": 3.196570981982404, "children": { "process_trajectory": { "total": 118.86490918003506, "count": 63693, "self": 118.63943903803533, "children": { "RLTrainer._checkpoint": { "total": 0.22547014199972182, "count": 2, "self": 0.22547014199972182 } } }, "_update_policy": { "total": 544.0205280739988, "count": 450, "self": 351.8034543890485, "children": { "TorchPPOOptimizer.update": { "total": 192.21707368495026, "count": 22809, "self": 192.21707368495026 } } } } } } }, "trainer_threads": { "total": 1.2399996194289997e-06, "count": 1, "self": 1.2399996194289997e-06 }, "TrainerController._save_models": { "total": 0.09551388900035818, "count": 1, "self": 0.0014478570001301705, "children": { "RLTrainer._checkpoint": { "total": 0.094066032000228, "count": 1, "self": 0.094066032000228 } } } } } } }