{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:59:44Z","timestamp":1730195984868,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"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":[[2023,9,26]]},"DOI":"10.1109\/allerton58177.2023.10313427","type":"proceedings-article","created":{"date-parts":[[2023,11,14]],"date-time":"2023-11-14T18:48:25Z","timestamp":1699987705000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["Best Policy Identification in Linear MDPs"],"prefix":"10.1109","author":[{"given":"J\u00e9r\u00f4me","family":"Taupin","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yassir","family":"Jedra","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandre","family":"Proutiere","sequence":"additional","affiliation":[{"name":"KTH Royal Institute of Technology,Stockholm,Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"04","article-title":"Finite-sample convergence rates for q-learning and indirect algorithms","volume":"11","author":"Kearns","year":"1999","journal-title":"Advances in Neural Information Processing"},{"key":"ref2","article-title":"On the sample complexity of reinforcement learning","volume-title":"PhD thesis","author":"Machandranath Kakade","year":"2003"},{"issue":"Jun","key":"ref3","first-page":"1079","article-title":"Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems","volume":"7","author":"Even-Dar","year":"2006","journal-title":"Journal of machine learning research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5368-1"},{"key":"ref5","first-page":"5186","article-title":"Near-optimal time and sample complexities for solving markov decision processes with a generative model","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Sidford","year":"2018"},{"key":"ref6","first-page":"67","article-title":"Model-based reinforcement learning with a generative model is minimax optimal","volume-title":"volume 125 of Proceedings of Machine Learning Research","author":"Agarwal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2023.2451"},{"key":"ref8","article-title":"Minimax optimal reinforcement learning for discounted mdps","author":"He","year":"2020","journal-title":"CoRR"},{"journal-title":"Sample complexity of episodic fixed-horizon reinforcement learning","year":"2015","author":"Dann","key":"ref9"},{"key":"ref10","article-title":"Episodic reinforcement learning in finite mdps: Minimax lower bounds revisited","author":"Domingues","year":"2020","journal-title":"CoRR"},{"journal-title":"Adaptive sampling for best policy identification in markov decision processes","year":"2020","author":"Marjani","key":"ref11"},{"journal-title":"Navigating to the best policy in markov decision processes","year":"2021","author":"Marjani","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1309"},{"key":"ref15","first-page":"4171","article-title":"Logarithmic regret for reinforcement learning with linear function approximation","volume-title":"International Conference on Machine Learning","author":"He"},{"article-title":"Reward-free rl is no harder than reward-aware rl in linear markov decision processes","year":"2022","author":"Wagenmaker","key":"ref16"},{"article-title":"Instance-dependent near-optimal policy identification in linear mdps via online experiment design","year":"2022","author":"Wagenmaker","key":"ref17"},{"key":"ref18","article-title":"Limiting extrapolation in linear approximate value iteration","volume":"32","author":"Zanette","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"6995","article-title":"Sample-optimal parametric q-learning using linearly additive features","volume-title":"International Conference on Machine Learning","author":"Yang"},{"key":"ref20","first-page":"5662","article-title":"Learning with good feature representations in bandits and in rl with a generative model","volume-title":"International Conference on Machine Learning","author":"Lattimore"},{"key":"ref21","first-page":"12793","article-title":"Provably efficient reinforcement learning for discounted mdps with feature mapping","volume-title":"International Conference on Machine Learning","author":"Zhou"},{"key":"ref22","article-title":"Best policy identification in linear mdps","volume-title":"Technical report","author":"Taupin","year":"2022"},{"key":"ref23","article-title":"Best-arm identification in linear bandits","volume":"27","author":"Soare","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"25852","article-title":"Navigating to the best policy in markov decision processes","volume":"34","author":"Al Marjani","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"10007","article-title":"Optimal best-arm identification in linear bandits","volume":"33","author":"Jedra","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","volume-title":"Handbook of Markov decision processes: methods and applications","volume":"40","author":"Feinberg","year":"2012"}],"event":{"name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","start":{"date-parts":[[2023,9,26]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2023,9,29]]}},"container-title":["2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10313338\/10313355\/10313427.pdf?arnumber=10313427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T16:30:54Z","timestamp":1709397054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10313427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/allerton58177.2023.10313427","relation":{},"subject":[],"published":{"date-parts":[[2023,9,26]]}}}