{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:22:41Z","timestamp":1774941761822,"version":"3.50.1"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut and Alice Wallenberg Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001729","name":"Swedish Foundation for Strategic Research","doi-asserted-by":"publisher","award":["2019-03606"],"award-info":[{"award-number":["2019-03606"]}],"id":[{"id":"10.13039\/501100001729","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,27]]},"DOI":"10.1109\/allerton49937.2022.9929353","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T21:34:30Z","timestamp":1667597670000},"page":"1-7","source":"Crossref","is-referenced-by-count":4,"title":["An Information-Theoretic Analysis of Bayesian Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Amaury","family":"Gouverneur","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Borja","family":"Rodriguez-Galvez","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.874"},{"key":"ref12","article-title":"An empirical evaluation of Thompson sampling","volume":"24","author":"chapelle","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"2069","article-title":"Optimistic bayesian sampling in contextual-bandit problems","volume":"13","author":"may","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref14","article-title":"(More) efficient reinforcement learning via posterior sampling","volume":"26","author":"osband","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849359"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-7970-4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"key":"ref18","article-title":"Lecture notes on Information Theory","author":"polyanskiy","year":"2017","journal-title":"MIT (6 441) UIUC (ECE 563) Yale (STAT 664)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0064610"},{"key":"ref4","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref3","article-title":"Policy gradi-ent methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1561\/2200000049","article-title":"Bayesian reinforcement learning: A survey","volume":"8","author":"ghavamzadeh","year":"2015","journal-title":"Foundations and Trends\ufffd in Machine Learning"},{"key":"ref8","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","author":"xu","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref7","author":"kallenberg","year":"2002","journal-title":"Probabilistic Symmetries and Invariance Principles"},{"key":"ref2","first-page":"2442","article-title":"An information-theoretic analysis of Thomp-son sampling","volume":"17","author":"russo","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3176056"},{"key":"ref9","article-title":"Tighter expected generalization error bounds via Wasserstein distance","volume":"34","author":"g\u00e1lvez","year":"2021","journal-title":"Ad-vances in Neural Information Processing Systems"}],"event":{"name":"2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2022,9,27]]},"end":{"date-parts":[[2022,9,30]]}},"container-title":["2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9929313\/9929314\/09929353.pdf?arnumber=9929353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:25:51Z","timestamp":1669667151000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9929353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/allerton49937.2022.9929353","relation":{},"subject":[],"published":{"date-parts":[[2022,9,27]]}}}