{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5550810098648071, "min": 0.5550810098648071, "max": 1.4549524784088135, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16705.71875, "min": 16705.71875, "max": 44137.4375, "count": 33 }, "Pyramids.Step.mean": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989989.0, "min": 29952.0, "max": 989989.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.20815089344978333, "min": -0.20830851793289185, "max": 0.26569387316703796, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 52.87032699584961, "min": -49.369117736816406, "max": 68.01763153076172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.029648320749402046, "min": -0.0008834694162942469, "max": 0.3101726472377777, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.530673503875732, "min": -0.22440123558044434, "max": 74.44143676757812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06422547127225527, "min": 0.06422547127225527, "max": 0.07369241788442846, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.8991565978115736, "min": 0.5036065107554026, "max": 1.0367416590306675, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010613081585082304, "min": 0.0005435335178195507, "max": 0.010758433663454208, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14858314219115226, "min": 0.00706593573165416, "max": 0.1568487180830904, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.343647552149993e-06, "min": 7.343647552149993e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001028110657300999, "min": 0.0001028110657300999, "max": 0.0032551899149368, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244785, "min": 0.10244785, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342698999999999, "min": 1.3691136000000002, "max": 2.4850632, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002545402149999998, "min": 0.0002545402149999998, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035635630099999966, "min": 0.0035635630099999966, "max": 0.10853781367999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01574070379137993, "min": 0.01574070379137993, "max": 0.44326528906822205, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2203698456287384, "min": 0.2203698456287384, "max": 3.1028571128845215, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 652.1020408163265, "min": 572.9019607843137, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31953.0, "min": 15984.0, "max": 32376.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.8988040433246263, "min": -1.0000000521540642, "max": 1.2309529036283493, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 44.041398122906685, "min": -32.000001668930054, "max": 62.778598085045815, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.8988040433246263, "min": -1.0000000521540642, "max": 1.2309529036283493, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 44.041398122906685, "min": -32.000001668930054, "max": 62.778598085045815, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10650282239271755, "min": 0.09400986044102923, "max": 8.753472724929452, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.21863829724316, "min": 4.418463440728374, "max": 140.05556359887123, "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": "1683287618", "python_version": "3.10.9 (main, Jan 11 2023, 15:21:40) [GCC 11.2.0]", "command_line_arguments": "/home/carlos/envs/rl/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": "2.0.0+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1683289483" }, "total": 1865.096950162988, "count": 1, "self": 0.3198623439820949, "children": { "run_training.setup": { "total": 0.025107505993219092, "count": 1, "self": 0.025107505993219092 }, "TrainerController.start_learning": { "total": 1864.7519803130126, "count": 1, "self": 1.0940710848663002, "children": { "TrainerController._reset_env": { "total": 4.959993616997963, "count": 1, "self": 4.959993616997963 }, "TrainerController.advance": { "total": 1858.6206374241447, "count": 63318, "self": 0.9503800779348239, "children": { "env_step": { "total": 1271.8935955229972, "count": 63318, "self": 1097.2502333575685, "children": { "SubprocessEnvManager._take_step": { "total": 173.87101907952456, "count": 63318, "self": 2.8534746569639537, "children": { "TorchPolicy.evaluate": { "total": 171.0175444225606, "count": 62543, "self": 171.0175444225606 } } }, "workers": { "total": 0.77234308590414, "count": 63318, "self": 0.0, "children": { "worker_root": { "total": 1862.141452107462, "count": 63318, "is_parallel": true, "self": 836.2211661949696, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012247859849594533, "count": 1, "is_parallel": true, "self": 0.00038421194767579436, "children": { "_process_rank_one_or_two_observation": { "total": 0.000840574037283659, "count": 8, "is_parallel": true, "self": 0.000840574037283659 } } }, "UnityEnvironment.step": { "total": 0.031713078991742805, "count": 1, "is_parallel": true, "self": 0.00031261699041351676, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00027608699747361243, "count": 1, "is_parallel": true, "self": 0.00027608699747361243 }, "communicator.exchange": { "total": 0.030084308004006743, "count": 1, "is_parallel": true, "self": 0.030084308004006743 }, "steps_from_proto": { "total": 0.001040066999848932, "count": 1, "is_parallel": true, "self": 0.00024592093541286886, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007941460644360632, "count": 8, "is_parallel": true, "self": 0.0007941460644360632 } } } } } } }, "UnityEnvironment.step": { "total": 1025.9202859124925, "count": 63317, "is_parallel": true, "self": 16.137900492059998, "children": { "UnityEnvironment._generate_step_input": { "total": 11.504071318689967, "count": 63317, "is_parallel": true, "self": 11.504071318689967 }, "communicator.exchange": { "total": 952.7787415915809, "count": 63317, "is_parallel": true, "self": 952.7787415915809 }, "steps_from_proto": { "total": 45.49957251016167, "count": 63317, "is_parallel": true, "self": 9.455112827883568, "children": { "_process_rank_one_or_two_observation": { "total": 36.0444596822781, "count": 506536, "is_parallel": true, "self": 36.0444596822781 } } } } } } } } } } }, "trainer_advance": { "total": 585.7766618232126, "count": 63318, "self": 1.884347304905532, "children": { "process_trajectory": { "total": 102.40647226801957, "count": 63318, "self": 102.2404203049955, "children": { "RLTrainer._checkpoint": { "total": 0.1660519630240742, "count": 2, "self": 0.1660519630240742 } } }, "_update_policy": { "total": 481.48584225028753, "count": 441, "self": 255.458057537704, "children": { "TorchPPOOptimizer.update": { "total": 226.02778471258353, "count": 22815, "self": 226.02778471258353 } } } } } } }, "trainer_threads": { "total": 5.610054358839989e-07, "count": 1, "self": 5.610054358839989e-07 }, "TrainerController._save_models": { "total": 0.07727762599824928, "count": 1, "self": 0.0008009509765543044, "children": { "RLTrainer._checkpoint": { "total": 0.07647667502169497, "count": 1, "self": 0.07647667502169497 } } } } } } }