{"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/contextual-bandits-with-smooth-regret","title":"Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces","arxiv_id":"2207.05849","date":"2022-07-12","proceeding":null,"authors":["Yinglun Zhu","Paul Mineiro"],"abstract":"Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and continuous control. While obtaining standard regret guarantees can be hopeless, alternative regret notions have been proposed to tackle the large action setting. We propose a smooth regret notion for contextual bandits, which dominates previously proposed alternatives. We design a statistically and computationally efficient algorithm -- for the proposed smooth regret -- that works with general function approximation under standard supervised oracles. We also present an adaptive algorithm that automatically adapts to any smoothness level. Our algorithms can be used to recover the previous minimax/Pareto optimal guarantees under the standard regret, e.g., in bandit problems with multiple best arms and Lipschitz/H{\\\"o}lder bandits. We conduct large-scale empirical evaluations demonstrating the efficacy of our proposed algorithms.","url_abs":"https://arxiv.org/abs/2207.05849v1","url_pdf":"https://arxiv.org/pdf/2207.05849v1.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":"contextual-bandits-with-smooth-regret","repo_url":"https://github.com/pmineiro/smoothcb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"information-retrieval","task_name":"Information Retrieval"},{"task_slug":"multi-armed-bandits","task_name":"Multi-Armed Bandits"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2207.05849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05849"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/pmineiro/smoothcb","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"18eff3f8c32328a0","entry":"CorralFastIGW","repo":"pmineiro/smoothcb","repo_kind":"official","path":"contextualbanditexperiment/tune-fastcbcorral.py","file_url":"https://github.com/pmineiro/smoothcb/blob/HEAD/contextualbanditexperiment/tune-fastcbcorral.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"18eff3f8c32328a0"}},{"code_sha256_prefix":"c0b1474e84292f49","entry":"makeCategoricalData","repo":"pmineiro/smoothcb","repo_kind":"official","path":"contextualbanditexperiment/tune-fastcbcorral.py","file_url":"https://github.com/pmineiro/smoothcb/blob/HEAD/contextualbanditexperiment/tune-fastcbcorral.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c0b1474e84292f49"}},{"code_sha256_prefix":"1a1b724938f6fdd4","entry":"floatorzero","repo":"pmineiro/smoothcb","repo_kind":"official","path":"contextualbanditexperiment/tune-fastcbcorral.py","file_url":"https://github.com/pmineiro/smoothcb/blob/HEAD/contextualbanditexperiment/tune-fastcbcorral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a1b724938f6fdd4"}},{"code_sha256_prefix":"fea89a181c2123e3","entry":"isfloat","repo":"pmineiro/smoothcb","repo_kind":"official","path":"contextualbanditexperiment/tune-fastcbcorral.py","file_url":"https://github.com/pmineiro/smoothcb/blob/HEAD/contextualbanditexperiment/tune-fastcbcorral.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fea89a181c2123e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}