{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T12:56:32Z","timestamp":1755694592263,"version":"3.37.3"},"reference-count":50,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["2007117","2003257"],"award-info":[{"award-number":["2007117","2003257"]}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1956276","CNS-2003131","CNS-2030026"],"award-info":[{"award-number":["CNS-1956276","CNS-2003131","CNS-2030026"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jsait.2024.3381818","type":"journal-article","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T18:27:05Z","timestamp":1711736825000},"page":"190-206","source":"Crossref","is-referenced-by-count":1,"title":["Toward General Function Approximation in Nonstationary Reinforcement Learning"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9062-3110","authenticated-orcid":false,"given":"Songtao","family":"Feng","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiquan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6403-212X","authenticated-orcid":false,"given":"Yu-Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California at Santa Barbara, Santa Barbara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6009-864X","authenticated-orcid":false,"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2631-4262","authenticated-orcid":false,"given":"Yingbin","family":"Liang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"9976","article-title":"Non-stationary reinforcement learning under general function approximation","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Feng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref5","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017","journal-title":"arXiv:1712.01815"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358027"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5229-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3328526.3329565"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/18.42174"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0397"},{"key":"ref16","first-page":"1","article-title":"Near-optimal regret bounds for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Auer"},{"key":"ref17","article-title":"A sliding-window algorithm for Markov decision processes with arbitrarily changing rewards and transitions","author":"Gajane","year":"2018","journal-title":"arXiv:1805.10066"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0396"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400662"},{"key":"ref20","first-page":"231","article-title":"The online loop-free stochastic shortest-path problem","volume-title":"Proc. Annu. Conf. Comput. Learn. Theory","author":"Neu"},{"key":"ref21","first-page":"805","article-title":"The adversarial stochastic shortest path problem with unknown transition probabilities","volume-title":"Proc. 15th Int. Conf. Artif. Intell. Stat.","author":"Neu"},{"key":"ref22","first-page":"1","article-title":"Online learning in episodic Markovian decision processes by relative entropy policy search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zimin"},{"key":"ref23","first-page":"675","article-title":"Better rates for any adversarial deterministic MDP","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Dekel"},{"key":"ref24","first-page":"5478","article-title":"Online convex optimization in adversarial Markov decision processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rosenberg"},{"key":"ref25","first-page":"4860","article-title":"Learning adversarial Markov decision processes with bandit feedback and unknown transition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref26","first-page":"1843","article-title":"Reinforcement learning for non-stationary Markov decision processes: The blessing of (More) optimism","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Cheung"},{"key":"ref27","first-page":"6743","article-title":"Dynamic regret of policy optimization in non-stationary environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fei"},{"key":"ref28","first-page":"7447","article-title":"Near-optimal model-free reinforcement learning in non-stationary episodic MDPs","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Mao"},{"key":"ref29","first-page":"3538","article-title":"A kernel-based approach to non-stationary reinforcement learning in metric spaces","volume-title":"Proc. Int. Conf. Artif. Intell. Stat.","author":"Domingues"},{"key":"ref30","article-title":"Nonstationary reinforcement learning with linear function approximation","author":"Zhou","year":"2020","journal-title":"arXiv:2010.04244"},{"key":"ref31","article-title":"Efficient learning in non-stationary linear Markov decision processes","author":"Touati","year":"2021","journal-title":"arXiv:2010.12870"},{"key":"ref32","article-title":"Optimistic policy optimization is provably efficient in non-stationary MDPs","author":"Zhong","year":"2022","journal-title":"arXiv:2110.08984"},{"key":"ref33","first-page":"13406","article-title":"Bellman eluder dimension: New rich classes of RL problems, and sample-efficient algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref34","article-title":"On the complexity of adversarial decision making","author":"Foster","year":"2022","journal-title":"arXiv:2206.13063"},{"key":"ref35","article-title":"Non-stationary reinforcement learning without prior knowledge: An optimal black-box approach","author":"Wei","year":"2021","journal-title":"arXiv:2102.05406"},{"key":"ref36","first-page":"1","article-title":"Eluder dimension and the sample complexity of optimistic exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Russo"},{"key":"ref37","first-page":"1","article-title":"Model-based reinforcement learning and the eluder dimension","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref38","article-title":"A general framework for sample-efficient function approximation in reinforcement learning","author":"Chen","year":"2022","journal-title":"arXiv:2209.15634"},{"key":"ref39","article-title":"The statistical complexity of interactive decision making","author":"Foster","year":"2023","journal-title":"arXiv:2112.13487"},{"key":"ref40","article-title":"\u221an-regret for learning in Markov decision processes with function approximation and low bellman rank","author":"Dong","year":"2020","journal-title":"arXiv:1909.02506"},{"key":"ref41","first-page":"1704","article-title":"Contextual decision processes with low {B}ellman rank are PAC-learnable","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref42","first-page":"2898","article-title":"Model-based RL in contextual decision processes: PAC bounds and exponential improvements over model-free approaches","volume-title":"Proc. 32nd Annu. Conf. Comput. Learn. Theory","author":"Sun"},{"key":"ref43","first-page":"2826","article-title":"Bilinear classes: A structural framework for provable generalization in RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref44","first-page":"6123","article-title":"Reinforcement learning with general value function approximation: Provably efficient approach via bounded eluder dimension","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_16"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref47","first-page":"1042","article-title":"Information-theoretic considerations in batch reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973075.50"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1993636.1993712"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973105.103"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/10461668\/10485378-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/10461668\/10485378.pdf?arnumber=10485378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T21:05:27Z","timestamp":1736543127000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10485378\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/jsait.2024.3381818","relation":{},"ISSN":["2641-8770"],"issn-type":[{"type":"electronic","value":"2641-8770"}],"subject":[],"published":{"date-parts":[[2024]]}}}