{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42775020003318787, "min": 0.42775020003318787, "max": 1.4091325998306274, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12846.1943359375, "min": 12846.1943359375, "max": 42747.4453125, "count": 33 }, "Pyramids.Step.mean": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989988.0, "min": 29952.0, "max": 989988.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4312892258167267, "min": -0.13221876323223114, "max": 0.4312892258167267, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 115.15422058105469, "min": -31.864723205566406, "max": 115.15422058105469, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.022867480292916298, "min": -0.022867480292916298, "max": 0.6111953854560852, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -6.105617046356201, "min": -6.105617046356201, "max": 144.85330200195312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07074742700933713, "min": 0.06682718109647796, "max": 0.07407502194661808, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9904639781307198, "min": 0.49190937563437087, "max": 1.0595341220061114, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014371763851765229, "min": 0.000980743006999391, "max": 0.019428840952589708, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2012046939247132, "min": 0.006865201048995736, "max": 0.21540256272191088, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.243961871092858e-06, "min": 7.243961871092858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010141546619530002, "min": 0.00010141546619530002, "max": 0.0033796337734555, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241462142857145, "min": 0.10241462142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338047000000003, "min": 1.3691136000000002, "max": 2.5724298, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002512206807142858, "min": 0.0002512206807142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003517089530000001, "min": 0.003517089530000001, "max": 0.11268179555, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015288310125470161, "min": 0.015288310125470161, "max": 0.7955248951911926, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21403634548187256, "min": 0.21403634548187256, "max": 5.568674087524414, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.86764705882354, "min": 394.04, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30591.0, "min": 15984.0, "max": 33606.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4324558561339098, "min": -1.0000000521540642, "max": 1.47257864544789, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 97.40699821710587, "min": -32.000001668930054, "max": 110.44339840859175, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4324558561339098, "min": -1.0000000521540642, "max": 1.47257864544789, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 97.40699821710587, "min": -32.000001668930054, "max": 110.44339840859175, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07169682549914903, "min": 0.06479260956839425, "max": 16.725277043879032, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.875384133942134, "min": 4.859445717629569, "max": 267.6044327020645, "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": "1766415921", "python_version": "3.10.12 (main, Oct 23 2025, 20:12:04) [GCC 13.3.0]", "command_line_arguments": "/home/rafe/Repositories/Hugging-Face-Courses/HF-venv-5/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1766438871" }, "total": 4650.192493431, "count": 1, "self": 0.32110766599998897, "children": { "run_training.setup": { "total": 0.040633937000052356, "count": 1, "self": 0.040633937000052356 }, "TrainerController.start_learning": { "total": 4649.830751828, "count": 1, "self": 3.4922469990060563, "children": { "TrainerController._reset_env": { "total": 3.0597714529999394, "count": 1, "self": 3.0597714529999394 }, "TrainerController.advance": { "total": 4643.235030900994, "count": 63659, "self": 3.464204882143349, "children": { "env_step": { "total": 3061.546612631926, "count": 63659, "self": 2837.3439267228855, "children": { "SubprocessEnvManager._take_step": { "total": 221.97938483902976, "count": 63659, "self": 10.71416561694025, "children": { "TorchPolicy.evaluate": { "total": 211.2652192220895, "count": 62571, "self": 211.2652192220895 } } }, "workers": { "total": 2.2233010700107343, "count": 63659, "self": 0.0, "children": { "worker_root": { "total": 4644.724209611026, "count": 63659, "is_parallel": true, "self": 2055.5355287640186, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023044869999466755, "count": 1, "is_parallel": true, "self": 0.0006607350001104351, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016437519998362404, "count": 8, "is_parallel": true, "self": 0.0016437519998362404 } } }, "UnityEnvironment.step": { "total": 0.07484420100001898, "count": 1, "is_parallel": true, "self": 0.0006106710001176907, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0015082799999390772, "count": 1, "is_parallel": true, "self": 0.0015082799999390772 }, "communicator.exchange": { "total": 0.07104501799994978, "count": 1, "is_parallel": true, "self": 0.07104501799994978 }, "steps_from_proto": { "total": 0.0016802320000124382, "count": 1, "is_parallel": true, "self": 0.0003954409999096242, "children": { "_process_rank_one_or_two_observation": { "total": 0.001284791000102814, "count": 8, "is_parallel": true, "self": 0.001284791000102814 } } } } } } }, "UnityEnvironment.step": { "total": 2589.188680847007, "count": 63658, "is_parallel": true, "self": 61.704469200995845, "children": { "UnityEnvironment._generate_step_input": { "total": 52.625308422971216, "count": 63658, "is_parallel": true, "self": 52.625308422971216 }, "communicator.exchange": { "total": 2298.4531354090623, "count": 63658, "is_parallel": true, "self": 2298.4531354090623 }, "steps_from_proto": { "total": 176.40576781397772, "count": 63658, "is_parallel": true, "self": 38.51783996386871, "children": { "_process_rank_one_or_two_observation": { "total": 137.887927850109, "count": 509264, "is_parallel": true, "self": 137.887927850109 } } } } } } } } } } }, "trainer_advance": { "total": 1578.2242133869247, "count": 63659, "self": 5.596806842001342, "children": { "process_trajectory": { "total": 273.1100640889256, "count": 63659, "self": 272.87232471592483, "children": { "RLTrainer._checkpoint": { "total": 0.23773937300074977, "count": 2, "self": 0.23773937300074977 } } }, "_update_policy": { "total": 1299.5173424559978, "count": 448, "self": 638.7056236529959, "children": { "TorchPPOOptimizer.update": { "total": 660.8117188030019, "count": 22788, "self": 660.8117188030019 } } } } } } }, "trainer_threads": { "total": 8.189999789465219e-07, "count": 1, "self": 8.189999789465219e-07 }, "TrainerController._save_models": { "total": 0.04370165599993925, "count": 1, "self": 0.0017102949996115058, "children": { "RLTrainer._checkpoint": { "total": 0.04199136100032774, "count": 1, "self": 0.04199136100032774 } } } } } } }