{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3102952241897583, "min": 0.30454158782958984, "max": 1.4764149188995361, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9418.0810546875, "min": 9043.6669921875, "max": 44788.5234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989993.0, "min": 29952.0, "max": 989993.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5284751057624817, "min": -0.09651791304349899, "max": 0.646522045135498, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 144.80218505859375, "min": -23.16429901123047, "max": 184.90530395507812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.033348482102155685, "min": -0.01714378409087658, "max": 0.31495872139930725, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.137483596801758, "min": -4.748828411102295, "max": 74.64521789550781, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0675561677198857, "min": 0.06520644967959184, "max": 0.07367452353648678, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9457863480783999, "min": 0.5157216647554075, "max": 1.0650019302916276, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014521736876174276, "min": 0.0006480201820093869, "max": 0.015912959387129548, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20330431626643986, "min": 0.008424262366122029, "max": 0.22278143141981369, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.418197527299995e-06, "min": 7.418197527299995e-06, "max": 0.00029523291587474284, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010385476538219993, "min": 0.00010385476538219993, "max": 0.0036328318890560996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024727, "min": 0.1024727, "max": 0.19841097142857142, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346178, "min": 1.3888768, "max": 2.6109439, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002570227299999999, "min": 0.0002570227299999999, "max": 0.009841256045714286, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035983182199999983, "min": 0.0035983182199999983, "max": 0.12111329560999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013241833075881004, "min": 0.013241833075881004, "max": 0.3928230106830597, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18538565933704376, "min": 0.18538565933704376, "max": 2.7497611045837402, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 351.4457831325301, "min": 294.65346534653463, "max": 996.71875, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29170.0, "min": 16751.0, "max": 32455.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5521421452243644, "min": -0.9351438009180129, "max": 1.6955999807307596, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 128.82779805362225, "min": -29.92460162937641, "max": 168.23899817466736, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5521421452243644, "min": -0.9351438009180129, "max": 1.6955999807307596, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 128.82779805362225, "min": -29.92460162937641, "max": 168.23899817466736, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.048140521151966036, "min": 0.042419247724009804, "max": 7.475783476058175, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.995663255613181, "min": 3.995663255613181, "max": 127.08831909298897, "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": "1689089307", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1689091629" }, "total": 2321.261840333, "count": 1, "self": 0.9587011140001778, "children": { "run_training.setup": { "total": 0.04554998600019644, "count": 1, "self": 0.04554998600019644 }, "TrainerController.start_learning": { "total": 2320.2575892329996, "count": 1, "self": 1.5935823269505818, "children": { "TrainerController._reset_env": { "total": 4.049705815000152, "count": 1, "self": 4.049705815000152 }, "TrainerController.advance": { "total": 2314.448032905049, "count": 64080, "self": 1.7072245560025294, "children": { "env_step": { "total": 1646.1051665650375, "count": 64080, "self": 1521.5808535869744, "children": { "SubprocessEnvManager._take_step": { "total": 123.57080820505121, "count": 64080, "self": 5.231265325085587, "children": { "TorchPolicy.evaluate": { "total": 118.33954287996562, "count": 62554, "self": 118.33954287996562 } } }, "workers": { "total": 0.9535047730119004, "count": 64080, "self": 0.0, "children": { "worker_root": { "total": 2314.7725745350094, "count": 64080, "is_parallel": true, "self": 918.4829426190431, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001966669000012189, "count": 1, "is_parallel": true, "self": 0.0006319660001281591, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013347029998840299, "count": 8, "is_parallel": true, "self": 0.0013347029998840299 } } }, "UnityEnvironment.step": { "total": 0.05454993800003649, "count": 1, "is_parallel": true, "self": 0.000560711999924024, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005360590000691445, "count": 1, "is_parallel": true, "self": 0.0005360590000691445 }, "communicator.exchange": { "total": 0.05130555599998843, "count": 1, "is_parallel": true, "self": 0.05130555599998843 }, "steps_from_proto": { "total": 0.0021476110000548942, "count": 1, "is_parallel": true, "self": 0.00038934300005166733, "children": { "_process_rank_one_or_two_observation": { "total": 0.001758268000003227, "count": 8, "is_parallel": true, "self": 0.001758268000003227 } } } } } } }, "UnityEnvironment.step": { "total": 1396.2896319159663, "count": 64079, "is_parallel": true, "self": 34.894041348936526, "children": { "UnityEnvironment._generate_step_input": { "total": 25.273906911049153, "count": 64079, "is_parallel": true, "self": 25.273906911049153 }, "communicator.exchange": { "total": 1222.3144232960442, "count": 64079, "is_parallel": true, "self": 1222.3144232960442 }, "steps_from_proto": { "total": 113.80726035993644, "count": 64079, "is_parallel": true, "self": 22.697565777895306, "children": { "_process_rank_one_or_two_observation": { "total": 91.10969458204113, "count": 512632, "is_parallel": true, "self": 91.10969458204113 } } } } } } } } } } }, "trainer_advance": { "total": 666.6356417840086, "count": 64080, "self": 2.985699104979858, "children": { "process_trajectory": { "total": 118.93023136402394, "count": 64080, "self": 118.66455056502377, "children": { "RLTrainer._checkpoint": { "total": 0.2656807990001653, "count": 2, "self": 0.2656807990001653 } } }, "_update_policy": { "total": 544.7197113150048, "count": 457, "self": 350.591992014007, "children": { "TorchPPOOptimizer.update": { "total": 194.1277193009978, "count": 22836, "self": 194.1277193009978 } } } } } } }, "trainer_threads": { "total": 1.3789999684377108e-06, "count": 1, "self": 1.3789999684377108e-06 }, "TrainerController._save_models": { "total": 0.16626680700028373, "count": 1, "self": 0.0019845280003210064, "children": { "RLTrainer._checkpoint": { "total": 0.16428227899996273, "count": 1, "self": 0.16428227899996273 } } } } } } }