{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.12421595305204391, "min": 0.10950485616922379, "max": 1.467787742614746, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3770.20263671875, "min": 3290.40185546875, "max": 44526.80859375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999897.0, "min": 29952.0, "max": 2999897.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999897.0, "min": 29952.0, "max": 2999897.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.837954580783844, "min": -0.164372980594635, "max": 0.9118956327438354, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 253.90023803710938, "min": -38.956398010253906, "max": 279.95196533203125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00010197670781053603, "min": -0.0487854965031147, "max": 0.5042665600776672, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.030898943543434143, "min": -14.538078308105469, "max": 119.51117706298828, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07002213082506344, "min": 0.0639570071627725, "max": 0.07342845711123207, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9803098315508881, "min": 0.4810576539308678, "max": 1.0814973009983075, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015918053890345618, "min": 0.000797987005765768, "max": 0.016221996341140337, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22285275446483865, "min": 0.009575844069189215, "max": 0.23288784317749864, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4959209299642858e-06, "min": 1.4959209299642858e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.09428930195e-05, "min": 2.09428930195e-05, "max": 0.003969489576836833, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049860714285715, "min": 0.10049860714285715, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069805, "min": 1.3962282666666668, "max": 2.7824909, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.98108535714286e-05, "min": 5.98108535714286e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008373519500000004, "min": 0.0008373519500000004, "max": 0.13232400035, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00916623417288065, "min": 0.008742894046008587, "max": 0.5092703700065613, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12832728028297424, "min": 0.12240051478147507, "max": 3.564892530441284, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 223.20567375886526, "min": 188.79333333333332, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31472.0, "min": 15984.0, "max": 32517.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7767943134333224, "min": -1.0000000521540642, "max": 1.7978331007507464, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 250.52799819409847, "min": -28.53800155967474, "max": 271.4727982133627, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7767943134333224, "min": -1.0000000521540642, "max": 1.7978331007507464, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 250.52799819409847, "min": -28.53800155967474, "max": 271.4727982133627, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02138673732029761, "min": 0.018469887106395667, "max": 10.431705193594098, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0155299621619633, "min": 2.7135124660562724, "max": 166.90728309750557, "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": "1741470963", "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": "1741478550" }, "total": 7587.741934903, "count": 1, "self": 0.5258827009984088, "children": { "run_training.setup": { "total": 0.019689299999981813, "count": 1, "self": 0.019689299999981813 }, "TrainerController.start_learning": { "total": 7587.196362902001, "count": 1, "self": 4.316460619076679, "children": { "TrainerController._reset_env": { "total": 2.814196895000123, "count": 1, "self": 2.814196895000123 }, "TrainerController.advance": { "total": 7579.977403037925, "count": 195782, "self": 4.647575989585675, "children": { "env_step": { "total": 5513.417661543389, "count": 195782, "self": 5043.276248387297, "children": { "SubprocessEnvManager._take_step": { "total": 467.72698401398634, "count": 195782, "self": 14.29324908388935, "children": { "TorchPolicy.evaluate": { "total": 453.433734930097, "count": 187574, "self": 453.433734930097 } } }, "workers": { "total": 2.414429142105746, "count": 195782, "self": 0.0, "children": { "worker_root": { "total": 7571.330239092194, "count": 195782, "is_parallel": true, "self": 2881.402848473229, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0026184099999682076, "count": 1, "is_parallel": true, "self": 0.0007448790001944872, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018735309997737204, "count": 8, "is_parallel": true, "self": 0.0018735309997737204 } } }, "UnityEnvironment.step": { "total": 0.046587789000113844, "count": 1, "is_parallel": true, "self": 0.0005289399998673616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004853400000683905, "count": 1, "is_parallel": true, "self": 0.0004853400000683905 }, "communicator.exchange": { "total": 0.04393811600016306, "count": 1, "is_parallel": true, "self": 0.04393811600016306 }, "steps_from_proto": { "total": 0.0016353930000150285, "count": 1, "is_parallel": true, "self": 0.0003539920001003338, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012814009999146947, "count": 8, "is_parallel": true, "self": 0.0012814009999146947 } } } } } } }, "UnityEnvironment.step": { "total": 4689.927390618965, "count": 195781, "is_parallel": true, "self": 99.2502156817045, "children": { "UnityEnvironment._generate_step_input": { "total": 72.12257761278374, "count": 195781, "is_parallel": true, "self": 72.12257761278374 }, "communicator.exchange": { "total": 4220.476706826913, "count": 195781, "is_parallel": true, "self": 4220.476706826913 }, "steps_from_proto": { "total": 298.07789049756275, "count": 195781, "is_parallel": true, "self": 61.34138726547735, "children": { "_process_rank_one_or_two_observation": { "total": 236.7365032320854, "count": 1566248, "is_parallel": true, "self": 236.7365032320854 } } } } } } } } } } }, "trainer_advance": { "total": 2061.9121655049503, "count": 195782, "self": 8.335089165191675, "children": { "process_trajectory": { "total": 400.85577975372394, "count": 195782, "self": 400.28109399172513, "children": { "RLTrainer._checkpoint": { "total": 0.5746857619988077, "count": 6, "self": 0.5746857619988077 } } }, "_update_policy": { "total": 1652.7212965860344, "count": 1397, "self": 906.4764607008567, "children": { "TorchPPOOptimizer.update": { "total": 746.2448358851777, "count": 68373, "self": 746.2448358851777 } } } } } } }, "trainer_threads": { "total": 1.0490002750884742e-06, "count": 1, "self": 1.0490002750884742e-06 }, "TrainerController._save_models": { "total": 0.08830130099886446, "count": 1, "self": 0.001705548998870654, "children": { "RLTrainer._checkpoint": { "total": 0.08659575199999381, "count": 1, "self": 0.08659575199999381 } } } } } } }