{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4224604368209839, "min": 0.41015860438346863, "max": 1.4517440795898438, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12680.572265625, "min": 12252.2578125, "max": 44040.109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29955.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29955.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4153847098350525, "min": -0.13148026168346405, "max": 0.42808446288108826, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.56925964355469, "min": -31.292301177978516, "max": 113.01429748535156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031819459050893784, "min": 0.006717985961586237, "max": 0.34291377663612366, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.62307357788086, "min": 1.726522445678711, "max": 81.61347961425781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06749992663195978, "min": 0.06606303311354539, "max": 0.07391170858549416, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0124988994793966, "min": 0.5603373674374748, "max": 1.0789463070458643, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012254997698215043, "min": 0.00017764149640808082, "max": 0.01602384718694657, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18382496547322566, "min": 0.0023093394533050507, "max": 0.22433386061725197, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.525697491466665e-06, "min": 7.525697491466665e-06, "max": 0.000294764176745275, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011288546237199998, "min": 0.00011288546237199998, "max": 0.0034944055351982003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250853333333335, "min": 0.10250853333333335, "max": 0.198254725, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376280000000002, "min": 1.4780484000000003, "max": 2.4648018, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026060247999999995, "min": 0.00026060247999999995, "max": 0.009825647027499999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003909037199999999, "min": 0.003909037199999999, "max": 0.11649369981999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010060147382318974, "min": 0.010060147382318974, "max": 0.3849566578865051, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15090221166610718, "min": 0.14163489639759064, "max": 3.079653263092041, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 435.18055555555554, "min": 425.859375, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31333.0, "min": 17521.0, "max": 33067.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4800844907130994, "min": -0.9999613423020609, "max": 1.485017626601107, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.08599884063005, "min": -31.99640166759491, "max": 105.08599884063005, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4800844907130994, "min": -0.9999613423020609, "max": 1.485017626601107, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.08599884063005, "min": -31.99640166759491, "max": 105.08599884063005, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.044431310145202435, "min": 0.044431310145202435, "max": 7.232109357913335, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.154623020309373, "min": 3.0103645500494167, "max": 130.17796844244003, "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": "1707896033", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707897725" }, "total": 1691.6612674570001, "count": 1, "self": 0.3727360720001798, "children": { "run_training.setup": { "total": 0.05172446599999603, "count": 1, "self": 0.05172446599999603 }, "TrainerController.start_learning": { "total": 1691.236806919, "count": 1, "self": 1.4421276859548016, "children": { "TrainerController._reset_env": { "total": 2.4619480579999617, "count": 1, "self": 2.4619480579999617 }, "TrainerController.advance": { "total": 1687.2471859610453, "count": 63615, "self": 1.5490380939809256, "children": { "env_step": { "total": 1104.9288046780762, "count": 63615, "self": 979.4269370771351, "children": { "SubprocessEnvManager._take_step": { "total": 124.61222899402514, "count": 63615, "self": 4.602445365955418, "children": { "TorchPolicy.evaluate": { "total": 120.00978362806973, "count": 62567, "self": 120.00978362806973 } } }, "workers": { "total": 0.8896386069159234, "count": 63615, "self": 0.0, "children": { "worker_root": { "total": 1689.060673647962, "count": 63615, "is_parallel": true, "self": 808.2099805659268, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001926987000160807, "count": 1, "is_parallel": true, "self": 0.0006131729996923241, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013138140004684828, "count": 8, "is_parallel": true, "self": 0.0013138140004684828 } } }, "UnityEnvironment.step": { "total": 0.036285045999875365, "count": 1, "is_parallel": true, "self": 0.00035883700024896825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003639279998424172, "count": 1, "is_parallel": true, "self": 0.0003639279998424172 }, "communicator.exchange": { "total": 0.03442563299995527, "count": 1, "is_parallel": true, "self": 0.03442563299995527 }, "steps_from_proto": { "total": 0.0011366479998287105, "count": 1, "is_parallel": true, "self": 0.00026913999977296044, "children": { "_process_rank_one_or_two_observation": { "total": 0.00086750800005575, "count": 8, "is_parallel": true, "self": 0.00086750800005575 } } } } } } }, "UnityEnvironment.step": { "total": 880.8506930820351, "count": 63614, "is_parallel": true, "self": 23.016375984991328, "children": { "UnityEnvironment._generate_step_input": { "total": 15.873605871968266, "count": 63614, "is_parallel": true, "self": 15.873605871968266 }, "communicator.exchange": { "total": 777.3959742330762, "count": 63614, "is_parallel": true, "self": 777.3959742330762 }, "steps_from_proto": { "total": 64.56473699199933, "count": 63614, "is_parallel": true, "self": 13.956460682834631, "children": { "_process_rank_one_or_two_observation": { "total": 50.608276309164694, "count": 508912, "is_parallel": true, "self": 50.608276309164694 } } } } } } } } } } }, "trainer_advance": { "total": 580.7693431889882, "count": 63615, "self": 2.6468081239672756, "children": { "process_trajectory": { "total": 115.42120229602324, "count": 63615, "self": 115.22695688202293, "children": { "RLTrainer._checkpoint": { "total": 0.19424541400030648, "count": 2, "self": 0.19424541400030648 } } }, "_update_policy": { "total": 462.70133276899764, "count": 451, "self": 268.304917175931, "children": { "TorchPPOOptimizer.update": { "total": 194.39641559306665, "count": 22776, "self": 194.39641559306665 } } } } } } }, "trainer_threads": { "total": 9.309997039963491e-07, "count": 1, "self": 9.309997039963491e-07 }, "TrainerController._save_models": { "total": 0.08554428300021755, "count": 1, "self": 0.0014424790001612564, "children": { "RLTrainer._checkpoint": { "total": 0.08410180400005629, "count": 1, "self": 0.08410180400005629 } } } } } } }