{"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/taming-the-monster-a-fast-and-simple","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","arxiv_id":"1402.0555","date":"2014-02-04","proceeding":null,"authors":["Alekh Agarwal","Daniel Hsu","Satyen Kale","John Langford","Lihong Li","Robert E. Schapire"],"abstract":"We present a new algorithm for the contextual bandit learning problem, where\nthe learner repeatedly takes one of $K$ actions in response to the observed\ncontext, and observes the reward only for that chosen action. Our method\nassumes access to an oracle for solving fully supervised cost-sensitive\nclassification problems and achieves the statistically optimal regret guarantee\nwith only $\\tilde{O}(\\sqrt{KT/\\log N})$ oracle calls across all $T$ rounds,\nwhere $N$ is the number of policies in the policy class we compete against. By\ndoing so, we obtain the most practical contextual bandit learning algorithm\namongst approaches that work for general policy classes. We further conduct a\nproof-of-concept experiment which demonstrates the excellent computational and\nprediction performance of (an online variant of) our algorithm relative to\nseveral baselines.","url_abs":"http://arxiv.org/abs/1402.0555v2","url_pdf":"http://arxiv.org/pdf/1402.0555v2.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":"taming-the-monster-a-fast-and-simple","repo_url":"https://github.com/VowpalWabbit/vowpal_wabbit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1402.0555","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}