{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1732717901468277, "min": 0.16883191466331482, "max": 1.4750075340270996, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5167.65771484375, "min": 5016.333984375, "max": 44745.828125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999998.0, "min": 29944.0, "max": 2999998.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999998.0, "min": 29944.0, "max": 2999998.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8625621795654297, "min": -0.10248949378728867, "max": 0.8698307275772095, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 271.70709228515625, "min": -24.59747886657715, "max": 271.70709228515625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004970206879079342, "min": -0.02576282247900963, "max": 0.41658225655555725, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.565615177154541, "min": -7.213590145111084, "max": 98.72999572753906, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808245780948531, "min": 0.0638794918890331, "max": 0.07363917369657837, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9531544093327943, "min": 0.4957619199670461, "max": 1.0592665975181814, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01619220309490853, "min": 5.462268124734433e-05, "max": 0.018284210662213373, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22669084332871944, "min": 0.0007100948562154763, "max": 0.25597894927098724, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5276709193809485e-06, "min": 1.5276709193809485e-06, "max": 0.0002984110862439238, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.138739287133328e-05, "min": 2.138739287133328e-05, "max": 0.0037592103469299325, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050919047619046, "min": 0.10050919047619046, "max": 0.19947036190476192, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071286666666665, "min": 1.3962925333333334, "max": 2.6774824000000006, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.086812857142845e-05, "min": 6.086812857142845e-05, "max": 0.009947089154285714, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008521537999999982, "min": 0.0008521537999999982, "max": 0.12532169966, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005503428168594837, "min": 0.005443856120109558, "max": 0.40362200140953064, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07704799622297287, "min": 0.07621398568153381, "max": 2.8253540992736816, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 192.23225806451612, "min": 192.23225806451612, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29796.0, "min": 16615.0, "max": 32833.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.8077677302783535, "min": -0.9999750521965325, "max": 1.8077677302783535, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 280.2039981931448, "min": -31.99920167028904, "max": 280.2039981931448, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.8077677302783535, "min": -0.9999750521965325, "max": 1.8077677302783535, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 280.2039981931448, "min": -31.99920167028904, "max": 280.2039981931448, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.011040707466646938, "min": 0.011040707466646938, "max": 8.34357355009107, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7113096573302755, "min": 1.611937693465734, "max": 141.8407503515482, "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": "1691108191", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691115862" }, "total": 7671.008981160001, "count": 1, "self": 0.5333794560010574, "children": { "run_training.setup": { "total": 0.05706278700006351, "count": 1, "self": 0.05706278700006351 }, "TrainerController.start_learning": { "total": 7670.418538917, "count": 1, "self": 4.3863660430461096, "children": { "TrainerController._reset_env": { "total": 5.0868495209999764, "count": 1, "self": 5.0868495209999764 }, "TrainerController.advance": { "total": 7660.843329399954, "count": 194826, "self": 4.426356907940317, "children": { "env_step": { "total": 5607.0756717761915, "count": 194826, "self": 5272.292259553346, "children": { "SubprocessEnvManager._take_step": { "total": 332.2392115490071, "count": 194826, "self": 14.541813471979935, "children": { "TorchPolicy.evaluate": { "total": 317.6973980770272, "count": 187558, "self": 317.6973980770272 } } }, "workers": { "total": 2.544200673837736, "count": 194826, "self": 0.0, "children": { "worker_root": { "total": 7653.047324228084, "count": 194826, "is_parallel": true, "self": 2739.9415117831577, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0028090659999406853, "count": 1, "is_parallel": true, "self": 0.000783813000111877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020252529998288082, "count": 8, "is_parallel": true, "self": 0.0020252529998288082 } } }, "UnityEnvironment.step": { "total": 0.045778663999954006, "count": 1, "is_parallel": true, "self": 0.0005522519999203723, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004893160000847274, "count": 1, "is_parallel": true, "self": 0.0004893160000847274 }, "communicator.exchange": { "total": 0.04286552700000357, "count": 1, "is_parallel": true, "self": 0.04286552700000357 }, "steps_from_proto": { "total": 0.0018715689999453389, "count": 1, "is_parallel": true, "self": 0.0003429679998134816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015286010001318573, "count": 8, "is_parallel": true, "self": 0.0015286010001318573 } } } } } } }, "UnityEnvironment.step": { "total": 4913.105812444926, "count": 194825, "is_parallel": true, "self": 106.07971303896011, "children": { "UnityEnvironment._generate_step_input": { "total": 69.742620872197, "count": 194825, "is_parallel": true, "self": 69.742620872197 }, "communicator.exchange": { "total": 4411.053334296899, "count": 194825, "is_parallel": true, "self": 4411.053334296899 }, "steps_from_proto": { "total": 326.23014423686993, "count": 194825, "is_parallel": true, "self": 64.20461575541594, "children": { "_process_rank_one_or_two_observation": { "total": 262.025528481454, "count": 1558600, "is_parallel": true, "self": 262.025528481454 } } } } } } } } } } }, "trainer_advance": { "total": 2049.3413007158224, "count": 194826, "self": 8.248276518858347, "children": { "process_trajectory": { "total": 350.4150544439759, "count": 194826, "self": 349.70366725497445, "children": { "RLTrainer._checkpoint": { "total": 0.7113871890014707, "count": 6, "self": 0.7113871890014707 } } }, "_update_policy": { "total": 1690.677969752988, "count": 1393, "self": 1105.4793974299164, "children": { "TorchPPOOptimizer.update": { "total": 585.1985723230715, "count": 68376, "self": 585.1985723230715 } } } } } } }, "trainer_threads": { "total": 9.539999155094847e-07, "count": 1, "self": 9.539999155094847e-07 }, "TrainerController._save_models": { "total": 0.10199299899977632, "count": 1, "self": 0.0013946660001238342, "children": { "RLTrainer._checkpoint": { "total": 0.10059833299965248, "count": 1, "self": 0.10059833299965248 } } } } } } }