{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5275444388389587, "min": 0.5229937434196472, "max": 1.4919500350952148, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15936.0615234375, "min": 15882.2734375, "max": 45259.796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989999.0, "min": 29952.0, "max": 989999.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.24824641644954681, "min": -0.11056908220052719, "max": 0.2682746946811676, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 64.29582214355469, "min": -26.536579132080078, "max": 69.75141906738281, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.10493466258049011, "min": -0.07974647730588913, "max": 0.2803550064563751, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 27.178077697753906, "min": -20.73408317565918, "max": 67.28520202636719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0689414441035462, "min": 0.06591482251279097, "max": 0.07353983002362968, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9651802174496468, "min": 0.46370742161550504, "max": 1.0899152256606612, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015097684056159136, "min": 8.922779325853028e-05, "max": 0.015097684056159136, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21136757678622792, "min": 0.000981505725843833, "max": 0.21136757678622792, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.250433297507145e-06, "min": 7.250433297507145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010150606616510002, "min": 0.00010150606616510002, "max": 0.0028984757338415, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241677857142858, "min": 0.10241677857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338349000000001, "min": 1.3691136000000002, "max": 2.2750194, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002514361792857143, "min": 0.0002514361792857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035201065100000004, "min": 0.0035201065100000004, "max": 0.09663923414999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009967753663659096, "min": 0.00953847449272871, "max": 0.44266510009765625, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13954855501651764, "min": 0.13579756021499634, "max": 3.0986557006835938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 569.0392156862745, "min": 552.1551724137931, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29021.0, "min": 15984.0, "max": 32430.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1563685945436066, "min": -1.0000000521540642, "max": 1.1563685945436066, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 58.97479832172394, "min": -32.000001668930054, "max": 61.969598077237606, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1563685945436066, "min": -1.0000000521540642, "max": 1.1563685945436066, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 58.97479832172394, "min": -32.000001668930054, "max": 61.969598077237606, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05858599430711383, "min": 0.05858599430711383, "max": 9.149884779006243, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9878857096628053, "min": 2.879139439028222, "max": 146.39815646409988, "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": "1714117409", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714120362" }, "total": 2953.092644154, "count": 1, "self": 0.6416723239999556, "children": { "run_training.setup": { "total": 0.07038534899993465, "count": 1, "self": 0.07038534899993465 }, "TrainerController.start_learning": { "total": 2952.380586481, "count": 1, "self": 2.1844519400378886, "children": { "TrainerController._reset_env": { "total": 2.758355896000012, "count": 1, "self": 2.758355896000012 }, "TrainerController.advance": { "total": 2947.350259628962, "count": 63199, "self": 2.49156530700202, "children": { "env_step": { "total": 1909.8899998869565, "count": 63199, "self": 1752.621921738913, "children": { "SubprocessEnvManager._take_step": { "total": 155.85631226405394, "count": 63199, "self": 6.920539922923126, "children": { "TorchPolicy.evaluate": { "total": 148.93577234113081, "count": 62556, "self": 148.93577234113081 } } }, "workers": { "total": 1.411765883989574, "count": 63199, "self": 0.0, "children": { "worker_root": { "total": 2945.3910633169517, "count": 63199, "is_parallel": true, "self": 1373.9750859968635, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004433328000231995, "count": 1, "is_parallel": true, "self": 0.0012978209997527301, "children": { "_process_rank_one_or_two_observation": { "total": 0.003135507000479265, "count": 8, "is_parallel": true, "self": 0.003135507000479265 } } }, "UnityEnvironment.step": { "total": 0.06658186599997862, "count": 1, "is_parallel": true, "self": 0.0008725630000299134, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005565849996855832, "count": 1, "is_parallel": true, "self": 0.0005565849996855832 }, "communicator.exchange": { "total": 0.0628538330001902, "count": 1, "is_parallel": true, "self": 0.0628538330001902 }, "steps_from_proto": { "total": 0.0022988850000729144, "count": 1, "is_parallel": true, "self": 0.0005538640011764073, "children": { "_process_rank_one_or_two_observation": { "total": 0.001745020998896507, "count": 8, "is_parallel": true, "self": 0.001745020998896507 } } } } } } }, "UnityEnvironment.step": { "total": 1571.4159773200881, "count": 63198, "is_parallel": true, "self": 50.64220372603086, "children": { "UnityEnvironment._generate_step_input": { "total": 32.037649113050065, "count": 63198, "is_parallel": true, "self": 32.037649113050065 }, "communicator.exchange": { "total": 1358.2502736570063, "count": 63198, "is_parallel": true, "self": 1358.2502736570063 }, "steps_from_proto": { "total": 130.48585082400086, "count": 63198, "is_parallel": true, "self": 27.809712724718793, "children": { "_process_rank_one_or_two_observation": { "total": 102.67613809928207, "count": 505584, "is_parallel": true, "self": 102.67613809928207 } } } } } } } } } } }, "trainer_advance": { "total": 1034.9686944350033, "count": 63199, "self": 3.9485818820444365, "children": { "process_trajectory": { "total": 161.0610769889604, "count": 63199, "self": 160.8682627499611, "children": { "RLTrainer._checkpoint": { "total": 0.19281423899928996, "count": 2, "self": 0.19281423899928996 } } }, "_update_policy": { "total": 869.9590355639984, "count": 424, "self": 355.27909520389085, "children": { "TorchPPOOptimizer.update": { "total": 514.6799403601076, "count": 22920, "self": 514.6799403601076 } } } } } } }, "trainer_threads": { "total": 9.129998943535611e-07, "count": 1, "self": 9.129998943535611e-07 }, "TrainerController._save_models": { "total": 0.08751810300054785, "count": 1, "self": 0.0022383310006262036, "children": { "RLTrainer._checkpoint": { "total": 0.08527977199992165, "count": 1, "self": 0.08527977199992165 } } } } } } }