{"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/thompson-sampling-for-contextual-bandits-with","title":"Thompson Sampling for Contextual Bandits with Linear Payoffs","arxiv_id":"1209.3352","date":"2012-09-15","proceeding":null,"authors":["Shipra Agrawal","Navin Goyal"],"abstract":"Thompson Sampling is one of the oldest heuristics for multi-armed bandit\nproblems. It is a randomized algorithm based on Bayesian ideas, and has\nrecently generated significant interest after several studies demonstrated it\nto have better empirical performance compared to the state-of-the-art methods.\nHowever, many questions regarding its theoretical performance remained open. In\nthis paper, we design and analyze a generalization of Thompson Sampling\nalgorithm for the stochastic contextual multi-armed bandit problem with linear\npayoff functions, when the contexts are provided by an adaptive adversary. This\nis among the most important and widely studied versions of the contextual\nbandits problem. We provide the first theoretical guarantees for the contextual\nversion of Thompson Sampling. We prove a high probability regret bound of\n$\\tilde{O}(d^{3/2}\\sqrt{T})$ (or $\\tilde{O}(d\\sqrt{T \\log(N)})$), which is the\nbest regret bound achieved by any computationally efficient algorithm available\nfor this problem in the current literature, and is within a factor of\n$\\sqrt{d}$ (or $\\sqrt{\\log(N)}$) of the information-theoretic lower bound for\nthis problem.","url_abs":"http://arxiv.org/abs/1209.3352v4","url_pdf":"http://arxiv.org/pdf/1209.3352v4.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":"thompson-sampling-for-contextual-bandits-with","repo_url":"https://github.com/PlaytikaOSS/pybandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"thompson-sampling-for-contextual-bandits-with","repo_url":"https://github.com/yanyangbaobeiIsEmma/Reinforcement-Learning-Contextual-Bandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"thompson-sampling","task_name":"Thompson Sampling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1209.3352","atlas_url":"https://app.syntology.ai/?focus=1209.3352","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}