{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:37Z","timestamp":1740169357809,"version":"3.37.3"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["No. 2021-0-01381","No.2022-0-00184"],"award-info":[{"award-number":["No. 2021-0-01381","No.2022-0-00184"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3404474","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T18:14:11Z","timestamp":1716488051000},"page":"100972-100982","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3533-4054","authenticated-orcid":false,"given":"Thanh","family":"Nguyen","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-7463","authenticated-orcid":false,"given":"Tung M.","family":"Luu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6820-4431","authenticated-orcid":false,"given":"Tri","family":"Ton","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2676-9454","authenticated-orcid":false,"given":"Sungwoong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0756-7179","authenticated-orcid":false,"given":"Chang D.","family":"Yoo","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Abbasi-Yadkori"},{"key":"ref2","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref3","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ITA.2018.8503252"},{"key":"ref5","first-page":"577","article-title":"Principled exploration via optimistic bootstrapping and backward induction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bai"},{"key":"ref6","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"Bai","year":"2022","journal-title":"arXiv:2202.11566"},{"key":"ref7","article-title":"The importance of pessimism in fixed-dataset policy optimization","author":"Buckman","year":"2020","journal-title":"arXiv:2009.06799"},{"key":"ref8","first-page":"3852","article-title":"Adversarially trained actor critic for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cheng"},{"key":"ref9","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chua"},{"key":"ref10","first-page":"172","article-title":"Action-gap phenomenon in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Farahmand"},{"key":"ref11","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref12","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref13","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Fujimoto"},{"key":"ref14","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn., (ICML)","volume":"80","author":"Fujimoto"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref16","first-page":"18267","article-title":"Why so pessimistic? Estimating uncertainties for offline RL through ensembles, and why their independence matters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Ghasemipour"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref18","article-title":"Training independent subnetworks for robust prediction","author":"Havasi","year":"2020","journal-title":"arXiv:2010.06610"},{"key":"ref19","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Janner"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref21","first-page":"5084","article-title":"Is pessimism provably efficient for offline RL?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref22","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref23","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref24","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref25","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref26","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref27","first-page":"5725","article-title":"Batch reinforcement learning with hyperparameter gradients","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref28","first-page":"6131","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref29","article-title":"Why M heads are better than one: Training a diverse ensemble of deep networks","author":"Lee","year":"2015","journal-title":"arXiv:1511.06314"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2006.05.029"},{"key":"ref31","article-title":"Deep ensembling with no overhead for either training or testing: The all-round blessings of dynamic sparsity","author":"Liu","year":"2021","journal-title":"arXiv:2106.14568"},{"key":"ref32","article-title":"Offline reinforcement learning with value-based episodic memory","author":"Ma","year":"2021","journal-title":"arXiv:2110.09796"},{"key":"ref33","first-page":"4424","article-title":"Distributional reinforcement learning for efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mavrin"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref35","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020","journal-title":"arXiv:2006.09359"},{"key":"ref36","article-title":"Information-directed exploration for deep reinforcement learning","author":"Nikolov","year":"2018","journal-title":"arXiv:1812.07544"},{"key":"ref37","first-page":"4026","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref38","article-title":"Implicit weight uncertainty in neural networks","author":"Pawlowski","year":"2017","journal-title":"arXiv:1711.01297"},{"key":"ref39","article-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","author":"Peng","year":"2019","journal-title":"arXiv:1910.00177"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00086"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20783"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2307\/2347982"},{"key":"ref43","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sekar"},{"article-title":"PEBL: Pessimistic ensembles for offline deep reinforcement learning","volume-title":"Proc. Robust Reliable Autonomy Wild Workshop 30th Int. Joint Conf. Artif. Intell.","author":"Smit","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00303"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref47","article-title":"Hydra: Preserving ensemble diversity for model distillation","author":"Tran","year":"2020","journal-title":"arXiv:2001.04694"},{"key":"ref48","article-title":"BatchEnsemble: An alternative approach to efficient ensemble and lifelong learning","author":"Wen","year":"2020","journal-title":"arXiv:2002.06715"},{"key":"ref49","article-title":"Flipout: Efficient pseudo-independent weight perturbations on mini-batches","author":"Wen","year":"2018","journal-title":"arXiv:1803.04386"},{"key":"ref50","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref51","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","author":"Wu","year":"2021","journal-title":"arXiv:2105.08140"},{"key":"ref52","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref53","article-title":"RORL: Robust offline reinforcement learning via conservative smoothing","author":"Yang","year":"2022","journal-title":"arXiv:2206.02829"},{"key":"ref54","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref55","first-page":"1719","article-title":"PLAS: Latent action space for offline reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Zhou"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10537203.pdf?arnumber=10537203","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T17:32:11Z","timestamp":1721928731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10537203\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3404474","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}