{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6166240572929382, "min": 0.6166240572929382, "max": 1.4610559940338135, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 18745.37109375, "min": 18745.37109375, "max": 44322.59375, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29982.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29982.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.31459179520606995, "min": -0.11372945457696915, "max": 0.31459179520606995, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 81.47927856445312, "min": -27.295068740844727, "max": 81.47927856445312, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.1749652922153473, "min": -0.1749652922153473, "max": 0.28640449047088623, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -45.316009521484375, "min": -45.316009521484375, "max": 69.02348327636719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792416374914216, "min": 0.06606042983353085, "max": 0.07335995397165261, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9509382924879902, "min": 0.5602740814976843, "max": 1.039693661331423, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014265168372644224, "min": 0.0005642948541346257, "max": 0.015190601559870212, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19971235721701913, "min": 0.006207243395480882, "max": 0.2278590233980532, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.406347531249999e-06, "min": 7.406347531249999e-06, "max": 0.00029506995164334997, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010368886543749998, "min": 0.00010368886543749998, "max": 0.0035070065309978997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246875000000001, "min": 0.10246875000000001, "max": 0.19835665, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345625000000002, "min": 1.4345625000000002, "max": 2.5690020999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025662812500000005, "min": 0.00025662812500000005, "max": 0.009835829335, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035927937500000004, "min": 0.0035927937500000004, "max": 0.11692330979000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016714874655008316, "min": 0.016714874655008316, "max": 0.4590266942977905, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23400825262069702, "min": 0.23400825262069702, "max": 3.672213554382324, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 533.0566037735849, "min": 533.0566037735849, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28252.0, "min": 16780.0, "max": 33208.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.0611925654941134, "min": -0.9999375520274043, "max": 1.183499964988894, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 57.30439853668213, "min": -31.998001664876938, "max": 63.90899810940027, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.0611925654941134, "min": -0.9999375520274043, "max": 1.183499964988894, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 57.30439853668213, "min": -31.998001664876938, "max": 63.90899810940027, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09229153331101837, "min": 0.09229153331101837, "max": 9.013456904639801, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.983742798794992, "min": 4.983742798794992, "max": 162.2422242835164, "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": "1688480122", "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": "1688482225" }, "total": 2102.786997524, "count": 1, "self": 0.47526047799965454, "children": { "run_training.setup": { "total": 0.03715892300010637, "count": 1, "self": 0.03715892300010637 }, "TrainerController.start_learning": { "total": 2102.274578123, "count": 1, "self": 1.327990988948386, "children": { "TrainerController._reset_env": { "total": 3.8829866920000313, "count": 1, "self": 3.8829866920000313 }, "TrainerController.advance": { "total": 2096.970990815051, "count": 63407, "self": 1.3446355780829435, "children": { "env_step": { "total": 1473.3729054049966, "count": 63407, "self": 1364.1995590339188, "children": { "SubprocessEnvManager._take_step": { "total": 108.38056753504998, "count": 63407, "self": 4.792143905035346, "children": { "TorchPolicy.evaluate": { "total": 103.58842363001463, "count": 62584, "self": 103.58842363001463 } } }, "workers": { "total": 0.7927788360277646, "count": 63407, "self": 0.0, "children": { "worker_root": { "total": 2097.321575851027, "count": 63407, "is_parallel": true, "self": 845.507585564063, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021120379999501893, "count": 1, "is_parallel": true, "self": 0.0005927930003508664, "children": { "_process_rank_one_or_two_observation": { "total": 0.001519244999599323, "count": 8, "is_parallel": true, "self": 0.001519244999599323 } } }, "UnityEnvironment.step": { "total": 0.04814240299992889, "count": 1, "is_parallel": true, "self": 0.0005378449998261203, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005014900000333, "count": 1, "is_parallel": true, "self": 0.0005014900000333 }, "communicator.exchange": { "total": 0.04516348900006051, "count": 1, "is_parallel": true, "self": 0.04516348900006051 }, "steps_from_proto": { "total": 0.0019395790000089619, "count": 1, "is_parallel": true, "self": 0.000391335000131221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015482439998777409, "count": 8, "is_parallel": true, "self": 0.0015482439998777409 } } } } } } }, "UnityEnvironment.step": { "total": 1251.8139902869639, "count": 63406, "is_parallel": true, "self": 32.632003283051745, "children": { "UnityEnvironment._generate_step_input": { "total": 23.36172030198577, "count": 63406, "is_parallel": true, "self": 23.36172030198577 }, "communicator.exchange": { "total": 1092.3348011259834, "count": 63406, "is_parallel": true, "self": 1092.3348011259834 }, "steps_from_proto": { "total": 103.48546557594295, "count": 63406, "is_parallel": true, "self": 20.465110925843874, "children": { "_process_rank_one_or_two_observation": { "total": 83.02035465009908, "count": 507248, "is_parallel": true, "self": 83.02035465009908 } } } } } } } } } } }, "trainer_advance": { "total": 622.2534498319715, "count": 63407, "self": 2.459630503976541, "children": { "process_trajectory": { "total": 109.25240635399632, "count": 63407, "self": 108.98354772799621, "children": { "RLTrainer._checkpoint": { "total": 0.26885862600011023, "count": 2, "self": 0.26885862600011023 } } }, "_update_policy": { "total": 510.5414129739986, "count": 450, "self": 328.13241796701664, "children": { "TorchPPOOptimizer.update": { "total": 182.40899500698197, "count": 22854, "self": 182.40899500698197 } } } } } } }, "trainer_threads": { "total": 9.19000285648508e-07, "count": 1, "self": 9.19000285648508e-07 }, "TrainerController._save_models": { "total": 0.09260870800017074, "count": 1, "self": 0.001377406000301562, "children": { "RLTrainer._checkpoint": { "total": 0.09123130199986917, "count": 1, "self": 0.09123130199986917 } } } } } } }