{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:43:23Z","timestamp":1779111803714,"version":"3.51.4"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"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":[[2023,3,22]]},"DOI":"10.1109\/ciss56502.2023.10089744","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T18:58:36Z","timestamp":1681153116000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Multi-armed Bandit Learning on a Graph"],"prefix":"10.1109","author":[{"given":"Tianpeng","family":"Zhang","sequence":"first","affiliation":[{"name":"Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasper","family":"Johansson","sequence":"additional","affiliation":[{"name":"Stanford University,Department of Electrical Engineering,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Li","sequence":"additional","affiliation":[{"name":"Harvard School of Engineering and Applied Sciences,Cambridge,MA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2016.1023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.171377"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS504"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3063886"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.0001.1800575"},{"issue":"51","key":"ref8","first-page":"1563","article-title":"Near-optimal regret bounds for reinforcement learning","volume":"11","author":"Jaksch","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","volume-title":"Multi-armed bandit learning on a graph","author":"Zhang","year":"2022"},{"key":"ref10","article-title":"Is q-learning provably efficient?","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Jin","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3380783"},{"key":"ref12","first-page":"3477","article-title":"Minimax regret of switching-constrained online convex optimization: No phase transition","volume":"33","author":"Chen","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Online learning in episodic markovian decision processes by relative entropy policy search","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Zimin","year":"2013"},{"key":"ref14","first-page":"22288","article-title":"Nearly minimax optimal reinforcement learning for discounted mdps","volume":"34","author":"He","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70, ser. ICML17","author":"Azar","year":"2017"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1266"},{"key":"ref17","first-page":"231","article-title":"The online loop-free stochastic shortest-path problem","volume":"2010","author":"Neu","year":"2010","journal-title":"COLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2013.2292137"},{"key":"ref19","article-title":"Dynamic programming and optimal control 4th edition, volume ii","author":"Bertsekas","year":"2015","journal-title":"Athena Scientific"},{"key":"ref20","first-page":"8210","article-title":"Near-optimal regret bounds for stochastic shortest path","volume-title":"International Conference on Machine Learning","author":"Rosenberg","year":"2020"},{"key":"ref21","first-page":"6843","article-title":"Stochastic shortest path: Minimax, parameter-free and towards horizon-free regret","volume":"34","author":"Tarbouriech","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"969","article-title":"Route planning under uncertainty: The canadian traveller problem","author":"Nikolova","year":"2008","journal-title":"AAAI"},{"key":"ref23","article-title":"Bandit algorithms for tree search","author":"Coquelin","year":"2007","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1040.0145"},{"key":"ref25","volume-title":"Introduction to algorithms","author":"Cormen","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/s0097539701398375"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-16-4589-1","volume-title":"Graph-Bandit","author":"Zhang","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"}],"event":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","location":"Baltimore, MD, USA","start":{"date-parts":[[2023,3,22]]},"end":{"date-parts":[[2023,3,24]]}},"container-title":["2023 57th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10089615\/10089616\/10089744.pdf?arnumber=10089744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T07:19:20Z","timestamp":1710400760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10089744\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/ciss56502.2023.10089744","relation":{},"subject":[],"published":{"date-parts":[[2023,3,22]]}}}