{"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/correlated-multi-armed-bandits-with-a-latent","title":"Correlated Multi-armed Bandits with a Latent Random Source","arxiv_id":"1808.05904","date":"2018-08-17","proceeding":null,"authors":["Samarth Gupta","Gauri Joshi","Osman Yağan"],"abstract":"We consider a novel multi-armed bandit framework where the rewards obtained\nby pulling the arms are functions of a common latent random variable. The\ncorrelation between arms due to the common random source can be used to design\na generalized upper-confidence-bound (UCB) algorithm that identifies certain\narms as $non-competitive$, and avoids exploring them. As a result, we reduce a\n$K$-armed bandit problem to a $C+1$-armed problem, where $C+1$ includes the\nbest arm and $C$ $competitive$ arms. Our regret analysis shows that the\ncompetitive arms need to be pulled $\\mathcal{O}(\\log T)$ times, while the\nnon-competitive arms are pulled only $\\mathcal{O}(1)$ times. As a result, there\nare regimes where our algorithm achieves a $\\mathcal{O}(1)$ regret as opposed\nto the typical logarithmic regret scaling of multi-armed bandit algorithms. We\nalso evaluate lower bounds on the expected regret and prove that our\ncorrelated-UCB algorithm achieves $\\mathcal{O}(1)$ regret whenever possible.","url_abs":"http://arxiv.org/abs/1808.05904v2","url_pdf":"http://arxiv.org/pdf/1808.05904v2.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":"correlated-multi-armed-bandits-with-a-latent","repo_url":"https://github.com/shreyasc-13/correlated_bandits","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"correlated-multi-armed-bandits-with-a-latent","repo_url":"https://github.com/ishank-juneja/Correlated-AoI-Bandits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.05904","atlas_url":"https://app.syntology.ai/?focus=1808.05904","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}