{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:53:14Z","timestamp":1763790794618,"version":"3.45.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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":[[2025,9,29]]},"DOI":"10.1109\/itw62417.2025.11240440","type":"proceedings-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:39:40Z","timestamp":1763750380000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Information-Theoretic Minimax Regret Upper Bounds for Reinforcement Learning Problems"],"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":"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":"10.1561\/2200000097"},{"key":"ref2","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"International Conference on machine learning","author":"Azar"},{"key":"ref3","article-title":"Is q-learning provably efficient?","volume-title":"Advances in neural information processing systems","volume":"31","author":"Jin"},{"key":"ref4","first-page":"15 198","article-title":"Almost optimal model-free reinforcement learningvia reference-advantage decomposition","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Zhang"},{"article-title":"The statistical complexity of interactive decision making","year":"2021","author":"Foster","key":"ref5"},{"key":"ref6","article-title":"Learning to optimize via information-directed sampling","volume-title":"Advances in Neural Information Processing Systems","volume":"27","author":"Russo"},{"issue":"68","key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton49937.2022.9929353"},{"key":"ref9","first-page":"2111","article-title":"An information-theoretic approach to minimax regret in partial monitoring","volume-title":"Conference on Learning Theory","author":"Lattimore"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1958.8.171"},{"key":"ref11","first-page":"266","article-title":"Bandit convex optimization:\\sqrtt regret in one dimension","volume-title":"Conference on Learning Theory","author":"Bubeck"},{"key":"ref12","first-page":"7511","article-title":"Minimax-bayes reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Buening"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889842"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-1090-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref16","article-title":"An information-theoretic analysis for Thompson sampling with many actions","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Dong"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49660.2025.10888239","article-title":"An information-theoretic analysis of Thompson sampling with infinite action spaces","author":"Gouverneur","year":"2025"},{"key":"ref18","first-page":"3","article-title":"Stochastic linear optimization under bandit feedback","volume":"2","author":"Dani","year":"2008","journal-title":"COLT"},{"key":"ref19","first-page":"28 575","article-title":"Regret bounds for information-directed reinforcement learning","volume-title":"Advances in neural information processing systems","volume":"35","author":"Hao"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"}],"event":{"name":"2025 IEEE Information Theory Workshop (ITW)","start":{"date-parts":[[2025,9,29]]},"location":"Sydney, Australia","end":{"date-parts":[[2025,10,3]]}},"container-title":["2025 IEEE Information Theory Workshop (ITW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240243\/11240249\/11240440.pdf?arnumber=11240440","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T05:48:20Z","timestamp":1763790500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240440\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/itw62417.2025.11240440","relation":{},"subject":[],"published":{"date-parts":[[2025,9,29]]}}}