{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30164167284965515, "min": 0.30164167284965515, "max": 1.3872199058532715, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9034.771484375, "min": 9034.771484375, "max": 42082.703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989956.0, "min": 29952.0, "max": 989956.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.003368256613612175, "min": -0.09132780134677887, "max": 0.3404161036014557, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -0.8252228498458862, "min": -22.010000228881836, "max": 89.52943420410156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.6514716148376465, "min": -4.42167854309082, "max": 0.45722198486328125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -404.61053466796875, "min": -1136.371337890625, "max": 120.24938201904297, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07037074958151648, "min": 0.06462560997247378, "max": 0.07250211167792302, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9851904941412308, "min": 0.48051184919681506, "max": 1.0170366373594115, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 1.7136813140221865, "min": 0.0008351562572567773, "max": 3.4419179982623134, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 23.99153839631061, "min": 0.005846093800797441, "max": 48.18685197567239, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.310818991664285e-06, "min": 7.310818991664285e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010235146588329999, "min": 0.00010235146588329999, "max": 0.003506198331267299, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10243690714285714, "min": 0.10243690714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341167, "min": 1.3691136000000002, "max": 2.6176721, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002534470235714286, "min": 0.0002534470235714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035482583300000007, "min": 0.0035482583300000007, "max": 0.11689639673, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004406671971082687, "min": 0.004406671971082687, "max": 0.5200653672218323, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06169340759515762, "min": 0.06169340759515762, "max": 3.6404573917388916, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 850.7142857142857, "min": 488.3898305084746, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29775.0, "min": 15984.0, "max": 32585.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.27958860439913613, "min": -1.0000000521540642, "max": 1.1927374708466232, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -9.785601153969765, "min": -32.000001668930054, "max": 76.33519813418388, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.27958860439913613, "min": -1.0000000521540642, "max": 1.1927374708466232, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -9.785601153969765, "min": -32.000001668930054, "max": 76.33519813418388, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042571697476419756, "min": 0.03502741596571468, "max": 10.428025946952403, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.4900094116746914, "min": 1.4900094116746914, "max": 166.84841515123844, "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": "1677676672", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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 --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677678972" }, "total": 2299.8091954189995, "count": 1, "self": 0.4431325139994442, "children": { "run_training.setup": { "total": 0.1959459740000966, "count": 1, "self": 0.1959459740000966 }, "TrainerController.start_learning": { "total": 2299.170116931, "count": 1, "self": 1.406129512994994, "children": { "TrainerController._reset_env": { "total": 6.304376191999836, "count": 1, "self": 6.304376191999836 }, "TrainerController.advance": { "total": 2291.374878508005, "count": 63519, "self": 1.448010674116631, "children": { "env_step": { "total": 1567.6856491798317, "count": 63519, "self": 1452.8211917665376, "children": { "SubprocessEnvManager._take_step": { "total": 114.04192062918082, "count": 63519, "self": 4.71423035420321, "children": { "TorchPolicy.evaluate": { "total": 109.32769027497761, "count": 62563, "self": 37.091357798996796, "children": { "TorchPolicy.sample_actions": { "total": 72.23633247598082, "count": 62563, "self": 72.23633247598082 } } } } }, "workers": { "total": 0.8225367841132538, "count": 63519, "self": 0.0, "children": { "worker_root": { "total": 2293.966024097939, "count": 63519, "is_parallel": true, "self": 959.1783317589261, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020415419994606054, "count": 1, "is_parallel": true, "self": 0.0007484560010198038, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012930859984408016, "count": 8, "is_parallel": true, "self": 0.0012930859984408016 } } }, "UnityEnvironment.step": { "total": 0.04755457499959448, "count": 1, "is_parallel": true, "self": 0.0005325649999576854, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047472099959122716, "count": 1, "is_parallel": true, "self": 0.00047472099959122716 }, "communicator.exchange": { "total": 0.044931307999831915, "count": 1, "is_parallel": true, "self": 0.044931307999831915 }, "steps_from_proto": { "total": 0.001615981000213651, "count": 1, "is_parallel": true, "self": 0.0004088219993718667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012071590008417843, "count": 8, "is_parallel": true, "self": 0.0012071590008417843 } } } } } } }, "UnityEnvironment.step": { "total": 1334.7876923390131, "count": 63518, "is_parallel": true, "self": 31.388689326024178, "children": { "UnityEnvironment._generate_step_input": { "total": 23.890762202056976, "count": 63518, "is_parallel": true, "self": 23.890762202056976 }, "communicator.exchange": { "total": 1185.0089890899271, "count": 63518, "is_parallel": true, "self": 1185.0089890899271 }, "steps_from_proto": { "total": 94.49925172100484, "count": 63518, "is_parallel": true, "self": 23.022190963196408, "children": { "_process_rank_one_or_two_observation": { "total": 71.47706075780843, "count": 508144, "is_parallel": true, "self": 71.47706075780843 } } } } } } } } } } }, "trainer_advance": { "total": 722.2412186540569, "count": 63519, "self": 2.648497806011619, "children": { "process_trajectory": { "total": 162.54423878405396, "count": 63519, "self": 162.30378199605366, "children": { "RLTrainer._checkpoint": { "total": 0.24045678800030146, "count": 2, "self": 0.24045678800030146 } } }, "_update_policy": { "total": 557.0484820639913, "count": 446, "self": 214.37177121203877, "children": { "TorchPPOOptimizer.update": { "total": 342.6767108519525, "count": 22791, "self": 342.6767108519525 } } } } } } }, "trainer_threads": { "total": 1.1680003808578476e-06, "count": 1, "self": 1.1680003808578476e-06 }, "TrainerController._save_models": { "total": 0.08473154999956023, "count": 1, "self": 0.0013658129992109025, "children": { "RLTrainer._checkpoint": { "total": 0.08336573700034933, "count": 1, "self": 0.08336573700034933 } } } } } } }