{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16895435750484467, "min": 0.1658705174922943, "max": 1.285115122795105, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5090.2568359375, "min": 4983.736328125, "max": 38985.25390625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999948.0, "min": 29977.0, "max": 2999948.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999948.0, "min": 29977.0, "max": 2999948.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7005521059036255, "min": -0.23684409260749817, "max": 0.9019624590873718, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 200.35791015625, "min": -56.368892669677734, "max": 273.29461669921875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009814852848649025, "min": -0.01684095710515976, "max": 0.33982905745506287, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8070478439331055, "min": -4.210239410400391, "max": 80.87931823730469, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07177237584532815, "min": 0.06507185840770845, "max": 0.07371932045224489, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0048132618345942, "min": 0.5897545636179591, "max": 1.0911975577245374, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015660363226613426, "min": 5.8158027445098536e-05, "max": 0.015785406252862667, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21924508517258798, "min": 0.0006397383018960839, "max": 0.2216416533434919, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5386423442952402e-06, "min": 1.5386423442952402e-06, "max": 0.0002984083380305542, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1540992820133364e-05, "min": 2.1540992820133364e-05, "max": 0.0036759616746794995, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051284761904762, "min": 0.10051284761904762, "max": 0.19946944583333337, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071798666666666, "min": 1.4071798666666666, "max": 2.647449966666667, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.123347714285722e-05, "min": 6.123347714285722e-05, "max": 0.00994699763875, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008572686800000012, "min": 0.0008572686800000012, "max": 0.12254951794999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004515998996794224, "min": 0.004246637225151062, "max": 0.4259420335292816, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06322398781776428, "min": 0.05956089124083519, "max": 3.407536268234253, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 266.4273504273504, "min": 208.15328467153284, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31172.0, "min": 15881.0, "max": 32842.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6480786207522082, "min": -0.999953385690848, "max": 1.786087578665601, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 192.82519862800837, "min": -31.998401656746864, "max": 247.2199980467558, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6480786207522082, "min": -0.999953385690848, "max": 1.786087578665601, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 192.82519862800837, "min": -31.998401656746864, "max": 247.2199980467558, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012732475680788146, "min": 0.009595334611517233, "max": 8.006417674274417, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4896996546522132, "min": 1.2683631910954318, "max": 128.10268278839067, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740163384", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740174781" }, "total": 11396.766216586999, "count": 1, "self": 1.3014343369995913, "children": { "run_training.setup": { "total": 0.0810897749997821, "count": 1, "self": 0.0810897749997821 }, "TrainerController.start_learning": { "total": 11395.383692475, "count": 1, "self": 7.207634512569712, "children": { "TrainerController._reset_env": { "total": 8.40742751200014, "count": 1, "self": 8.40742751200014 }, "TrainerController.advance": { "total": 11379.671726612429, "count": 194740, "self": 7.833692758460529, "children": { "env_step": { "total": 7863.462162996745, "count": 194740, "self": 7334.75621588766, "children": { "SubprocessEnvManager._take_step": { "total": 524.3247359350244, "count": 194740, "self": 23.91212984892627, "children": { "TorchPolicy.evaluate": { "total": 500.4126060860981, "count": 187571, "self": 500.4126060860981 } } }, "workers": { "total": 4.381211174060809, "count": 194740, "self": 0.0, "children": { "worker_root": { "total": 11370.013521714991, "count": 194740, "is_parallel": true, "self": 4605.230234007891, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007214713000394113, "count": 1, "is_parallel": true, "self": 0.005377999000302225, "children": { "_process_rank_one_or_two_observation": { "total": 0.001836714000091888, "count": 8, "is_parallel": true, "self": 0.001836714000091888 } } }, "UnityEnvironment.step": { "total": 0.14860673299972404, "count": 1, "is_parallel": true, "self": 0.0006917159998920397, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005893520001336583, "count": 1, "is_parallel": true, "self": 0.0005893520001336583 }, "communicator.exchange": { "total": 0.14394126899969706, "count": 1, "is_parallel": true, "self": 0.14394126899969706 }, "steps_from_proto": { "total": 0.0033843960000012885, "count": 1, "is_parallel": true, "self": 0.001776528000846156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016078679991551326, "count": 8, "is_parallel": true, "self": 0.0016078679991551326 } } } } } } }, "UnityEnvironment.step": { "total": 6764.7832877071, "count": 194739, "is_parallel": true, "self": 148.68857727247178, "children": { "UnityEnvironment._generate_step_input": { "total": 96.04235109036381, "count": 194739, "is_parallel": true, "self": 96.04235109036381 }, "communicator.exchange": { "total": 6120.382586824768, "count": 194739, "is_parallel": true, "self": 6120.382586824768 }, "steps_from_proto": { "total": 399.6697725194963, "count": 194739, "is_parallel": true, "self": 88.0759782631576, "children": { "_process_rank_one_or_two_observation": { "total": 311.5937942563387, "count": 1557912, "is_parallel": true, "self": 311.5937942563387 } } } } } } } } } } }, "trainer_advance": { "total": 3508.375870857224, "count": 194740, "self": 15.707852324461783, "children": { "process_trajectory": { "total": 534.9657887938056, "count": 194740, "self": 533.9845537188066, "children": { "RLTrainer._checkpoint": { "total": 0.9812350749989491, "count": 6, "self": 0.9812350749989491 } } }, "_update_policy": { "total": 2957.7022297389567, "count": 1378, "self": 1159.738114325135, "children": { "TorchPPOOptimizer.update": { "total": 1797.9641154138217, "count": 68496, "self": 1797.9641154138217 } } } } } } }, "trainer_threads": { "total": 1.158001396106556e-06, "count": 1, "self": 1.158001396106556e-06 }, "TrainerController._save_models": { "total": 0.09690267999940261, "count": 1, "self": 0.002352113999222638, "children": { "RLTrainer._checkpoint": { "total": 0.09455056600017997, "count": 1, "self": 0.09455056600017997 } } } } } } }