{"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/double-thompson-sampling-for-dueling-bandits","title":"Double Thompson Sampling for Dueling Bandits","arxiv_id":"1604.07101","date":"2016-04-25","proceeding":"NeurIPS 2016 12","authors":["Huasen Wu","Xin Liu"],"abstract":"In this paper, we propose a Double Thompson Sampling (D-TS) algorithm for\ndueling bandit problems. As indicated by its name, D-TS selects both the first\nand the second candidates according to Thompson Sampling. Specifically, D-TS\nmaintains a posterior distribution for the preference matrix, and chooses the\npair of arms for comparison by sampling twice from the posterior distribution.\nThis simple algorithm applies to general Copeland dueling bandits, including\nCondorcet dueling bandits as its special case. For general Copeland dueling\nbandits, we show that D-TS achieves $O(K^2 \\log T)$ regret. For Condorcet\ndueling bandits, we further simplify the D-TS algorithm and show that the\nsimplified D-TS algorithm achieves $O(K \\log T + K^2 \\log \\log T)$ regret.\nSimulation results based on both synthetic and real-world data demonstrate the\nefficiency of the proposed D-TS algorithm.","url_abs":"http://arxiv.org/abs/1604.07101v2","url_pdf":"http://arxiv.org/pdf/1604.07101v2.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":"double-thompson-sampling-for-dueling-bandits","repo_url":"https://github.com/HuasenWu/DuelingBandits","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.07101","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}