{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4058502912521362, "min": 1.4058502912521362, "max": 1.427981972694397, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70718.484375, "min": 67893.4609375, "max": 79360.578125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.25961538461539, "min": 77.4392523364486, "max": 403.272, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50055.0, "min": 48932.0, "max": 50409.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999901.0, "min": 49974.0, "max": 1999901.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999901.0, "min": 49974.0, "max": 1999901.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4798808097839355, "min": 0.1469809114933014, "max": 2.4798808097839355, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1289.5379638671875, "min": 18.22563362121582, "max": 1577.298583984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7620675430848047, "min": 1.8603671113810232, "max": 3.9866265900732225, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1956.2751224040985, "min": 230.68552181124687, "max": 2494.4350928664207, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7620675430848047, "min": 1.8603671113810232, "max": 3.9866265900732225, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1956.2751224040985, "min": 230.68552181124687, "max": 2494.4350928664207, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018335936668477697, "min": 0.013246521755354478, "max": 0.0189249074299975, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05500781000543309, "min": 0.026493043510708955, "max": 0.05579549614728117, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050984988982478774, "min": 0.021466064639389514, "max": 0.059503489173948765, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15295496694743632, "min": 0.04293212927877903, "max": 0.1724236981322368, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5456488181499975e-06, "min": 3.5456488181499975e-06, "max": 0.00029536545154485003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0636946454449992e-05, "min": 1.0636946454449992e-05, "max": 0.0008441707686097501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118185, "min": 0.10118185, "max": 0.19845515000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30354555, "min": 0.20751620000000004, "max": 0.5813902499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.897431499999995e-05, "min": 6.897431499999995e-05, "max": 0.004922911985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020692294499999986, "min": 0.00020692294499999986, "max": 0.014071373475000001, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710655783", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --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": "1710658371" }, "total": 2588.644932595, "count": 1, "self": 0.4355823389996658, "children": { "run_training.setup": { "total": 0.05304912299999387, "count": 1, "self": 0.05304912299999387 }, "TrainerController.start_learning": { "total": 2588.156301133, "count": 1, "self": 4.813167092133426, "children": { "TrainerController._reset_env": { "total": 2.8934579689999964, "count": 1, "self": 2.8934579689999964 }, "TrainerController.advance": { "total": 2580.322669450866, "count": 232571, "self": 4.992602866845573, "children": { "env_step": { "total": 2079.806300741023, "count": 232571, "self": 1725.4415795160671, "children": { "SubprocessEnvManager._take_step": { "total": 351.0654547259741, "count": 232571, "self": 18.116870476050167, "children": { "TorchPolicy.evaluate": { "total": 332.94858424992395, "count": 222984, "self": 332.94858424992395 } } }, "workers": { "total": 3.299266498981467, "count": 232571, "self": 0.0, "children": { "worker_root": { "total": 2580.23895054199, "count": 232571, "is_parallel": true, "self": 1187.9821693828071, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009466249999832144, "count": 1, "is_parallel": true, "self": 0.00025600099996836434, "children": { "_process_rank_one_or_two_observation": { "total": 0.00069062400001485, "count": 2, "is_parallel": true, "self": 0.00069062400001485 } } }, "UnityEnvironment.step": { "total": 0.03665996499995572, "count": 1, "is_parallel": true, "self": 0.0006246869999699811, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002160369999728573, "count": 1, "is_parallel": true, "self": 0.0002160369999728573 }, "communicator.exchange": { "total": 0.03492108500000768, "count": 1, "is_parallel": true, "self": 0.03492108500000768 }, "steps_from_proto": { "total": 0.0008981560000052013, "count": 1, "is_parallel": true, "self": 0.00026745800005301135, "children": { "_process_rank_one_or_two_observation": { "total": 0.00063069799995219, "count": 2, "is_parallel": true, "self": 0.00063069799995219 } } } } } } }, "UnityEnvironment.step": { "total": 1392.256781159183, "count": 232570, "is_parallel": true, "self": 41.71165254618654, "children": { "UnityEnvironment._generate_step_input": { "total": 91.42903467898742, "count": 232570, "is_parallel": true, "self": 91.42903467898742 }, "communicator.exchange": { "total": 1160.35913106105, "count": 232570, "is_parallel": true, "self": 1160.35913106105 }, "steps_from_proto": { "total": 98.75696287295898, "count": 232570, "is_parallel": true, "self": 37.30266673607713, "children": { "_process_rank_one_or_two_observation": { "total": 61.45429613688185, "count": 465140, "is_parallel": true, "self": 61.45429613688185 } } } } } } } } } } }, "trainer_advance": { "total": 495.52376584299776, "count": 232571, "self": 7.309722181090024, "children": { "process_trajectory": { "total": 167.27695518690905, "count": 232571, "self": 165.96130034490955, "children": { "RLTrainer._checkpoint": { "total": 1.3156548419995033, "count": 10, "self": 1.3156548419995033 } } }, "_update_policy": { "total": 320.9370884749987, "count": 97, "self": 257.3126481320005, "children": { "TorchPPOOptimizer.update": { "total": 63.624440342998184, "count": 2910, "self": 63.624440342998184 } } } } } } }, "trainer_threads": { "total": 7.920002644823398e-07, "count": 1, "self": 7.920002644823398e-07 }, "TrainerController._save_models": { "total": 0.12700582900015434, "count": 1, "self": 0.001963587999853189, "children": { "RLTrainer._checkpoint": { "total": 0.12504224100030115, "count": 1, "self": 0.12504224100030115 } } } } } } }