{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3706507086753845, "min": 0.3201614320278168, "max": 1.473378300666809, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11066.1474609375, "min": 9615.087890625, "max": 44696.40234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3331144154071808, "min": -0.09107375144958496, "max": 0.39633625745773315, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 86.94286346435547, "min": -21.85770034790039, "max": 106.2181167602539, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.09083788841962814, "min": -0.009213448502123356, "max": 0.5094258189201355, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 23.708688735961914, "min": -2.4692041873931885, "max": 120.73391723632812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07064189648760172, "min": 0.06535820750290297, "max": 0.07251598730451728, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0596284473140258, "min": 0.484753852743246, "max": 1.0596284473140258, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015099906016095904, "min": 0.0001312281195939244, "max": 0.015099906016095904, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22649859024143856, "min": 0.0017059655547210172, "max": 0.22649859024143856, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.463217512293334e-06, "min": 7.463217512293334e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011194826268440001, "min": 0.00011194826268440001, "max": 0.0032242963252346, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248770666666668, "min": 0.10248770666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373156000000001, "min": 1.3691136000000002, "max": 2.3465145, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002585218960000001, "min": 0.0002585218960000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038778284400000015, "min": 0.0038778284400000015, "max": 0.10748906346, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012315409258008003, "min": 0.012315409258008003, "max": 0.4367673695087433, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1847311407327652, "min": 0.17616669833660126, "max": 3.0573716163635254, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 542.1578947368421, "min": 431.4848484848485, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30903.0, "min": 15984.0, "max": 32564.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2472561179545887, "min": -1.0000000521540642, "max": 1.4224567000768078, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 71.09359872341156, "min": -32.000001668930054, "max": 95.30459890514612, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2472561179545887, "min": -1.0000000521540642, "max": 1.4224567000768078, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 71.09359872341156, "min": -32.000001668930054, "max": 95.30459890514612, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06914588277791872, "min": 0.05696006811922416, "max": 9.196979328989983, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.941315318341367, "min": 3.816324563988019, "max": 147.15166926383972, "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": "1694573604", "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": "1694575962" }, "total": 2358.624215243, "count": 1, "self": 0.6888729110000895, "children": { "run_training.setup": { "total": 0.04233354200005124, "count": 1, "self": 0.04233354200005124 }, "TrainerController.start_learning": { "total": 2357.89300879, "count": 1, "self": 1.5159373589476672, "children": { "TrainerController._reset_env": { "total": 4.939138793999973, "count": 1, "self": 4.939138793999973 }, "TrainerController.advance": { "total": 2351.3361816420534, "count": 63449, "self": 1.5173412360732073, "children": { "env_step": { "total": 1671.8953572779806, "count": 63449, "self": 1549.3217041699577, "children": { "SubprocessEnvManager._take_step": { "total": 121.61312975200417, "count": 63449, "self": 5.186604125066651, "children": { "TorchPolicy.evaluate": { "total": 116.42652562693752, "count": 62573, "self": 116.42652562693752 } } }, "workers": { "total": 0.9605233560187116, "count": 63449, "self": 0.0, "children": { "worker_root": { "total": 2352.0056621680005, "count": 63449, "is_parallel": true, "self": 929.5978483140088, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018363060000865516, "count": 1, "is_parallel": true, "self": 0.0005778019997251249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012585040003614267, "count": 8, "is_parallel": true, "self": 0.0012585040003614267 } } }, "UnityEnvironment.step": { "total": 0.07776645700005247, "count": 1, "is_parallel": true, "self": 0.0005520969998542569, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000518081000109305, "count": 1, "is_parallel": true, "self": 0.000518081000109305 }, "communicator.exchange": { "total": 0.07401479800000743, "count": 1, "is_parallel": true, "self": 0.07401479800000743 }, "steps_from_proto": { "total": 0.002681481000081476, "count": 1, "is_parallel": true, "self": 0.00035293699988869776, "children": { "_process_rank_one_or_two_observation": { "total": 0.002328544000192778, "count": 8, "is_parallel": true, "self": 0.002328544000192778 } } } } } } }, "UnityEnvironment.step": { "total": 1422.4078138539917, "count": 63448, "is_parallel": true, "self": 36.07077551703878, "children": { "UnityEnvironment._generate_step_input": { "total": 25.33581198395791, "count": 63448, "is_parallel": true, "self": 25.33581198395791 }, "communicator.exchange": { "total": 1242.6829039170134, "count": 63448, "is_parallel": true, "self": 1242.6829039170134 }, "steps_from_proto": { "total": 118.3183224359816, "count": 63448, "is_parallel": true, "self": 23.642911625147235, "children": { "_process_rank_one_or_two_observation": { "total": 94.67541081083436, "count": 507584, "is_parallel": true, "self": 94.67541081083436 } } } } } } } } } } }, "trainer_advance": { "total": 677.9234831279994, "count": 63449, "self": 2.7316912120350025, "children": { "process_trajectory": { "total": 121.02998828296722, "count": 63449, "self": 120.80581630396682, "children": { "RLTrainer._checkpoint": { "total": 0.22417197900040264, "count": 2, "self": 0.22417197900040264 } } }, "_update_policy": { "total": 554.1618036329971, "count": 437, "self": 359.9821181699883, "children": { "TorchPPOOptimizer.update": { "total": 194.1796854630088, "count": 22803, "self": 194.1796854630088 } } } } } } }, "trainer_threads": { "total": 1.1209995136596262e-06, "count": 1, "self": 1.1209995136596262e-06 }, "TrainerController._save_models": { "total": 0.10174987399932434, "count": 1, "self": 0.0014693670000269776, "children": { "RLTrainer._checkpoint": { "total": 0.10028050699929736, "count": 1, "self": 0.10028050699929736 } } } } } } }