{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/regret-lower-bound-and-optimal-algorithm-in","title":"Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem","arxiv_id":"1506.02550","date":"2015-06-08","proceeding":null,"authors":["Junpei Komiyama","Junya Honda","Hisashi Kashima","Hiroshi Nakagawa"],"abstract":"We study the $K$-armed dueling bandit problem, a variation of the standard\nstochastic bandit problem where the feedback is limited to relative comparisons\nof a pair of arms. We introduce a tight asymptotic regret lower bound that is\nbased on the information divergence. An algorithm that is inspired by the\nDeterministic Minimum Empirical Divergence algorithm (Honda and Takemura, 2010)\nis proposed, and its regret is analyzed. The proposed algorithm is found to be\nthe first one with a regret upper bound that matches the lower bound.\nExperimental comparisons of dueling bandit algorithms show that the proposed\nalgorithm significantly outperforms existing ones.","url_abs":"http://arxiv.org/abs/1506.02550v3","url_pdf":"http://arxiv.org/pdf/1506.02550v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"regret-lower-bound-and-optimal-algorithm-in","repo_url":"https://github.com/jkomiyama/duelingbanditlib","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}