{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T03:24:59Z","timestamp":1777519499158,"version":"3.51.4"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:p>In an offline reinforcement learning setting, the safe policy improvement (SPI) problem aims to improve the performance of a behavior policy according to which sample data has been generated.\n\nState-of-the-art approaches to SPI require a high number of samples to provide practical probabilistic guarantees on the improved policy's performance.\n\nWe present a novel approach to the SPI problem that provides the means to require less data for such guarantees.\n\nSpecifically, to prove the correctness of these guarantees, we devise implicit transformations on the data set and the underlying environment model that serve as theoretical foundations to derive tighter improvement bounds for SPI.\n\nOur empirical evaluation, using the well-established SPI with baseline bootstrapping (SPIBB) algorithm, on standard benchmarks shows that our method indeed significantly reduces the sample complexity of the SPIBB algorithm.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/490","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"4406-4415","source":"Crossref","is-referenced-by-count":4,"title":["More for Less: Safe Policy Improvement with Stronger Performance Guarantees"],"prefix":"10.24963","author":[{"given":"Patrick","family":"Wienh\u00f6ft","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Dresden, Dresden, Germany"},{"name":"Centre for Tactile Internet with Human-in-the-Loop (CeTI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marnix","family":"Suilen","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thiago D.","family":"Sim\u00e3o","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Clemens","family":"Dubslaff","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"},{"name":"Centre for Tactile Internet with Human-in-the-Loop (CeTI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christel","family":"Baier","sequence":"additional","affiliation":[{"name":"Technische Universit\u00e4t Dresden, Dresden, Germany"},{"name":"Centre for Tactile Internet with Human-in-the-Loop (CeTI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nils","family":"Jansen","sequence":"additional","affiliation":[{"name":"Radboud University, Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","theme":"Artificial Intelligence","location":"Macau, SAR China","acronym":"IJCAI-2023","number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2023,8,19]]},"end":{"date-parts":[[2023,8,25]]}},"container-title":["Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:49:49Z","timestamp":1691743789000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/490"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2023\/490","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}