{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T16:50:02Z","timestamp":1774716602449,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889842","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Information-Theoretic Minimax Regret Bounds for Reinforcement Learning based on Duality"],"prefix":"10.1109","author":[{"given":"Raghav","family":"Bongole","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amaury","family":"Gouverneur","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Borja","family":"Rodr\u00edguez-G\u00e1lvez","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias J.","family":"Oechtering","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikael","family":"Skoglund","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref3","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"International conference on machine learning","author":"Azar"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/e25101394"},{"key":"ref5","first-page":"3998","article-title":"Rate- distortion analysis of minimum excess risk in bayesian learning","volume-title":"International Conference on Machine Learning","author":"Hafez-Kolahi"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3176056"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3249636"},{"key":"ref8","first-page":"2111","article-title":"An information-theoretic approach to minimax regret in partial monitoring","volume-title":"Conference on Learning Theory","author":"Lattimore"},{"key":"ref9","first-page":"7511","article-title":"Minimax-bayes reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Buening"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton49937.2022.9929353"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref12","article-title":"Probability measures on metric spaces","author":"Van Gaans","year":"2003","journal-title":"Lecture notes"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF01117474"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1090-5"},{"issue":"68","key":"ref15","first-page":"1","article-title":"An information-theoretic analysis of Thompson sampling","volume":"17","author":"Russo","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","article-title":"An empirical evaluation of Thompson sampling","volume":"24","author":"Chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT54713.2023.10206792"},{"key":"ref18","article-title":"An information-theoretic analysis for Thompson sampling with many actions","volume":"31","author":"Dong","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"The statistical complexity of interactive decision making","author":"Foster","year":"2021"},{"key":"ref20","first-page":"217","article-title":"Minimax policies for adversarial and stochastic bandits","volume-title":"COLT","author":"Audibert"},{"key":"ref21","first-page":"3199","article-title":"Beyond UCB: Optimal and efficient contextual bandits with regression oracles","volume-title":"International Conference on Machine Learning","author":"Foster"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889842.pdf?arnumber=10889842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:08Z","timestamp":1774416368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889842","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}