{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T04:41:26Z","timestamp":1773376886721,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,7]],"date-time":"2024-07-07T00:00:00Z","timestamp":1720310400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,7]]},"DOI":"10.1109\/isit57864.2024.10619458","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T13:25:01Z","timestamp":1724073901000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Towards General Function Approximation in Nonstationary Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Songtao","family":"Feng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruiquan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Xiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingbin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Non-stationary reinforcement learning under general function approximation","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Feng","year":"2023"},{"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":"Ar Xiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2983149"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358027"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5229-0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3328526.3329565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/18.42174"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0397"},{"key":"ref15","article-title":"Near-optimal regret bounds for reinforcement learning","author":"Auer","year":"2008","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"A sliding-window algorithm for markov decision processes with arbitrarily changing rewards and transitions","author":"Gajane","year":"2018","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1090.0396"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2009.5400662"},{"key":"ref19","article-title":"The online loop-free stochastic shortest-path problem","volume-title":"Annual Conference Computational Learning Theory","author":"Neu","year":"2010"},{"key":"ref20","article-title":"The adversarial stochastic shortest path problem with unknown transition probabilities","volume-title":"Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics","author":"Neu","year":"2012"},{"key":"ref21","article-title":"Online learning in episodic markovian decision processes by relative entropy policy search","author":"Zimin","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Better rates for any adversarial deterministic MDP","volume-title":"Proceedings of the 30th International Conference on Machine Learning","author":"Dekel","year":"2013"},{"key":"ref23","article-title":"Online convex opti-mization in adversarial markov decision processes","volume-title":"International Conference on Machine Learning","author":"Rosenberg","year":"2019"},{"key":"ref24","article-title":"Learning ad-versarial markov decision processes with bandit feedback and unknown transition","volume-title":"International Conference on Machine Learning","author":"Jin","year":"2020"},{"key":"ref25","article-title":"Rein-forcement learning for non-stationary Markov decision processes: The blessing of (More) optimism","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Cheung","year":"2020"},{"key":"ref26","article-title":"Dynamic regret of policy optimization in non-stationary environments","author":"Fei","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Near-optimal model-free reinforcement learning in nonstationary episodic MDPs","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Mao","year":"2021"},{"key":"ref28","article-title":"A kernel-based approach to non-stationary reinforcement learning in metric spaces","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Domingues","year":"2020"},{"key":"ref29","article-title":"Nonstationary reinforcement learning with linear function approximation","author":"Zhou","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref30","article-title":"Efficient learning in non-stationary linear markov decision processes","author":"Touati","year":"2020","journal-title":"ArXiv"},{"key":"ref31","article-title":"Op-timistic policy optimization is provably efficient in non-stationary MDPs","author":"Zhong","year":"2021","journal-title":"ArXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref33","article-title":"On the Complexity of Adversarial Decision Making","author":"Foster","year":"2022","journal-title":"ArXiv"},{"key":"ref34","article-title":"Non-stationary reinforcement learning without prior knowledge: An optimal black-box approach","author":"Wei","year":"2021","journal-title":"ArXiv"},{"key":"ref35","article-title":"Reinforce-ment learning with general value function approximation: Provably efficient approach via bounded eluder dimension","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","article-title":"Eluder dimension and the sample complexity of optimistic exploration","author":"Russo","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","article-title":"Reinforce-ment learning with general value function approximation: Provably efficient approach via bounded eluder dimension","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973075.50"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1993636.1993712"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973105.103"}],"event":{"name":"2024 IEEE International Symposium on Information Theory (ISIT)","location":"Athens, Greece","start":{"date-parts":[[2024,7,7]]},"end":{"date-parts":[[2024,7,12]]}},"container-title":["2024 IEEE International Symposium on Information Theory (ISIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10619013\/10619074\/10619458.pdf?arnumber=10619458","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T20:29:00Z","timestamp":1773347340000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10619458\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,7]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/isit57864.2024.10619458","relation":{},"subject":[],"published":{"date-parts":[[2024,7,7]]}}}