{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5544239282608032, "min": 0.5544239282608032, "max": 1.4804720878601074, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16668.201171875, "min": 16668.201171875, "max": 44911.6015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30720406770706177, "min": -0.09272222220897675, "max": 0.30720406770706177, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 79.25865173339844, "min": -22.438777923583984, "max": 80.10205078125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05198511853814125, "min": -0.05136161297559738, "max": 0.4627130329608917, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 13.412160873413086, "min": -13.456742286682129, "max": 109.6629867553711, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06746010744645185, "min": 0.06525129824395344, "max": 0.07371842501673935, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.944441504250326, "min": 0.5016560816024056, "max": 1.0327607453412686, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01590906463500914, "min": 0.000316650339836971, "max": 0.01590906463500914, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22272690489012797, "min": 0.0037998040780436518, "max": 0.22272690489012797, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.367004687221428e-06, "min": 7.367004687221428e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010313806562109999, "min": 0.00010313806562109999, "max": 0.0035072417309194993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245563571428572, "min": 0.10245563571428572, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343789, "min": 1.3691136000000002, "max": 2.5690804999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002553180078571428, "min": 0.0002553180078571428, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035744521099999992, "min": 0.0035744521099999992, "max": 0.11693114195, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009702242910861969, "min": 0.009391454048454762, "max": 0.3962453305721283, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13583140075206757, "min": 0.13583140075206757, "max": 2.7737174034118652, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 511.1111111111111, "min": 503.0952380952381, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27600.0, "min": 15984.0, "max": 32571.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2594188312595744, "min": -1.0000000521540642, "max": 1.2594188312595744, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 66.74919805675745, "min": -32.000001668930054, "max": 74.29959836602211, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2594188312595744, "min": -1.0000000521540642, "max": 1.2594188312595744, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 66.74919805675745, "min": -32.000001668930054, "max": 74.29959836602211, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05318665779960388, "min": 0.0490993660845099, "max": 8.279884029179811, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8188928633790056, "min": 2.8188928633790056, "max": 132.47814446687698, "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": "1705549238", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705551602" }, "total": 2364.5201285870003, "count": 1, "self": 0.5452934969998751, "children": { "run_training.setup": { "total": 0.05425849399989602, "count": 1, "self": 0.05425849399989602 }, "TrainerController.start_learning": { "total": 2363.9205765960005, "count": 1, "self": 1.5448789630609099, "children": { "TrainerController._reset_env": { "total": 2.883804895999674, "count": 1, "self": 2.883804895999674 }, "TrainerController.advance": { "total": 2359.40603280894, "count": 63364, "self": 1.6081694138529201, "children": { "env_step": { "total": 1698.5048213051073, "count": 63364, "self": 1554.6324893689957, "children": { "SubprocessEnvManager._take_step": { "total": 142.90826377501526, "count": 63364, "self": 5.288055364071624, "children": { "TorchPolicy.evaluate": { "total": 137.62020841094363, "count": 62570, "self": 137.62020841094363 } } }, "workers": { "total": 0.9640681610962929, "count": 63364, "self": 0.0, "children": { "worker_root": { "total": 2358.1940710380572, "count": 63364, "is_parallel": true, "self": 939.2176638751071, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002277224999943428, "count": 1, "is_parallel": true, "self": 0.0006452990010075155, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016319259989359125, "count": 8, "is_parallel": true, "self": 0.0016319259989359125 } } }, "UnityEnvironment.step": { "total": 0.0990013870000439, "count": 1, "is_parallel": true, "self": 0.0005712810002478363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005035859999225067, "count": 1, "is_parallel": true, "self": 0.0005035859999225067 }, "communicator.exchange": { "total": 0.09610575799979415, "count": 1, "is_parallel": true, "self": 0.09610575799979415 }, "steps_from_proto": { "total": 0.0018207620000794122, "count": 1, "is_parallel": true, "self": 0.00040474099978382583, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014160210002955864, "count": 8, "is_parallel": true, "self": 0.0014160210002955864 } } } } } } }, "UnityEnvironment.step": { "total": 1418.9764071629502, "count": 63363, "is_parallel": true, "self": 37.43008776197075, "children": { "UnityEnvironment._generate_step_input": { "total": 27.161011549959312, "count": 63363, "is_parallel": true, "self": 27.161011549959312 }, "communicator.exchange": { "total": 1243.9815886220458, "count": 63363, "is_parallel": true, "self": 1243.9815886220458 }, "steps_from_proto": { "total": 110.4037192289743, "count": 63363, "is_parallel": true, "self": 23.076767019810177, "children": { "_process_rank_one_or_two_observation": { "total": 87.32695220916412, "count": 506904, "is_parallel": true, "self": 87.32695220916412 } } } } } } } } } } }, "trainer_advance": { "total": 659.2930420899797, "count": 63364, "self": 2.931171458021254, "children": { "process_trajectory": { "total": 136.39527950697266, "count": 63364, "self": 136.15370416897258, "children": { "RLTrainer._checkpoint": { "total": 0.24157533800007513, "count": 2, "self": 0.24157533800007513 } } }, "_update_policy": { "total": 519.9665911249858, "count": 444, "self": 310.525372385001, "children": { "TorchPPOOptimizer.update": { "total": 209.44121873998483, "count": 22869, "self": 209.44121873998483 } } } } } } }, "trainer_threads": { "total": 9.530003808322363e-07, "count": 1, "self": 9.530003808322363e-07 }, "TrainerController._save_models": { "total": 0.08585897499960993, "count": 1, "self": 0.0014467370001511881, "children": { "RLTrainer._checkpoint": { "total": 0.08441223799945874, "count": 1, "self": 0.08441223799945874 } } } } } } }