{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35719534754753113, "min": 0.35719534754753113, "max": 1.054766058921814, "count": 30 }, "Pyramids.Policy.Entropy.sum": { "value": 10698.71484375, "min": 10698.71484375, "max": 31592.3515625, "count": 30 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 119902.0, "max": 989965.0, "count": 30 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 119902.0, "max": 989965.0, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5460983514785767, "min": -0.0974889025092125, "max": 0.5460983514785767, "count": 30 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.72314453125, "min": -22.812402725219727, "max": 150.72314453125, "count": 30 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0029611587524414062, "min": 0.0023736939765512943, "max": 0.07181325554847717, "count": 30 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8172798156738281, "min": 0.5886760950088501, "max": 16.804302215576172, "count": 30 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06743303105985331, "min": 0.06466054770300174, "max": 0.0725224927841087, "count": 30 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0114954658977997, "min": 0.46330883616953555, "max": 1.0617936914079074, "count": 30 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016359856022690012, "min": 0.0009069478663576594, "max": 0.016875319805140385, "count": 30 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.24539784034035017, "min": 0.006348635064503616, "max": 0.24539784034035017, "count": 30 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.827430058221778e-06, "min": 7.827430058221778e-06, "max": 0.00026814349570518055, "count": 30 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011741145087332666, "min": 0.00011741145087332666, "max": 0.0032590894245260738, "count": 30 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1026091108891109, "min": 0.1026091108891109, "max": 0.18938116169544747, "count": 30 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5391366633366634, "min": 1.3256681318681323, "max": 2.5730535464535467, "count": 30 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002706501778221779, "min": 0.0002706501778221779, "max": 0.008939178053375197, "count": 30 }, "Pyramids.Policy.Beta.sum": { "value": 0.004059752667332668, "min": 0.004059752667332668, "max": 0.10866766739260741, "count": 30 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010596213862299919, "min": 0.010596213862299919, "max": 0.05572683736681938, "count": 30 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15894320607185364, "min": 0.1507917195558548, "max": 0.44880765676498413, "count": 30 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 345.97701149425285, "min": 330.7471264367816, "max": 992.96875, "count": 30 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30100.0, "min": 16669.0, "max": 33014.0, "count": 30 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5390482581723695, "min": -0.8687938018701971, "max": 1.626804979518056, "count": 30 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 133.89719846099615, "min": -27.801401659846306, "max": 139.22339843958616, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5390482581723695, "min": -0.8687938018701971, "max": 1.626804979518056, "count": 30 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 133.89719846099615, "min": -27.801401659846306, "max": 139.22339843958616, "count": 30 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03831589446823252, "min": 0.03751143765279183, "max": 0.6441118344664574, "count": 30 }, "Pyramids.Policy.RndReward.sum": { "value": 3.333482818736229, "min": 3.263495075792889, "max": 14.810292342677712, "count": 30 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1792043045", "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 Training1 --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1792045080" }, "total": 2035.2300666610001, "count": 1, "self": 0.5320186540002396, "children": { "run_training.setup": { "total": 0.02697980999982974, "count": 1, "self": 0.02697980999982974 }, "TrainerController.start_learning": { "total": 2034.671068197, "count": 1, "self": 1.3648352698892268, "children": { "TrainerController._reset_env": { "total": 2.198292009999932, "count": 1, "self": 2.198292009999932 }, "TrainerController.advance": { "total": 2031.026351016111, "count": 58256, "self": 1.4436706751428119, "children": { "env_step": { "total": 1469.680813124974, "count": 58256, "self": 1322.8473327629906, "children": { "SubprocessEnvManager._take_step": { "total": 145.99700289595467, "count": 58256, "self": 4.4204590790118345, "children": { "TorchPolicy.evaluate": { "total": 141.57654381694283, "count": 56971, "self": 141.57654381694283 } } }, "workers": { "total": 0.8364774660287821, "count": 58256, "self": 0.0, "children": { "worker_root": { "total": 2031.5064243439722, "count": 58256, "is_parallel": true, "self": 818.0495413049255, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019142979999742238, "count": 1, "is_parallel": true, "self": 0.000626249000106327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012880489998678968, "count": 8, "is_parallel": true, "self": 0.0012880489998678968 } } }, "UnityEnvironment.step": { "total": 0.05611606100001154, "count": 1, "is_parallel": true, "self": 0.0005923270000494085, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005188140000882413, "count": 1, "is_parallel": true, "self": 0.0005188140000882413 }, "communicator.exchange": { "total": 0.05312563400002546, "count": 1, "is_parallel": true, "self": 0.05312563400002546 }, "steps_from_proto": { "total": 0.0018792859998484346, "count": 1, "is_parallel": true, "self": 0.00042257899917785835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014567070006705762, "count": 8, "is_parallel": true, "self": 0.0014567070006705762 } } } } } } }, "UnityEnvironment.step": { "total": 1213.4568830390467, "count": 58255, "is_parallel": true, "self": 31.57155091002437, "children": { "UnityEnvironment._generate_step_input": { "total": 22.433926825032586, "count": 58255, "is_parallel": true, "self": 22.433926825032586 }, "communicator.exchange": { "total": 1061.4991053719941, "count": 58255, "is_parallel": true, "self": 1061.4991053719941 }, "steps_from_proto": { "total": 97.95229993199564, "count": 58255, "is_parallel": true, "self": 20.042960317003917, "children": { "_process_rank_one_or_two_observation": { "total": 77.90933961499172, "count": 466040, "is_parallel": true, "self": 77.90933961499172 } } } } } } } } } } }, "trainer_advance": { "total": 559.9018672159941, "count": 58256, "self": 2.7851908119555446, "children": { "process_trajectory": { "total": 103.17694592803332, "count": 58256, "self": 102.98077208403288, "children": { "RLTrainer._checkpoint": { "total": 0.19617384400044102, "count": 2, "self": 0.19617384400044102 } } }, "_update_policy": { "total": 453.93973047600525, "count": 417, "self": 240.49118897404492, "children": { "TorchPPOOptimizer.update": { "total": 213.44854150196034, "count": 20757, "self": 213.44854150196034 } } } } } } }, "trainer_threads": { "total": 1.3499998203769792e-06, "count": 1, "self": 1.3499998203769792e-06 }, "TrainerController._save_models": { "total": 0.08158855100009532, "count": 1, "self": 0.001377993999994942, "children": { "RLTrainer._checkpoint": { "total": 0.08021055700010038, "count": 1, "self": 0.08021055700010038 } } } } } } }