{"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/non-stationary-bandits-and-meta-learning-with","title":"Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms","arxiv_id":"2202.13001","date":"2022-02-25","proceeding":null,"authors":["MohammadJavad Azizi","Thang Duong","Yasin Abbasi-Yadkori","András György","Claire Vernade","Mohammad Ghavamzadeh"],"abstract":"We study a sequential decision problem where the learner faces a sequence of $K$-armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unknown (the non-stationary bandit setting). For a given integer $M\\le K$, the learner aims to compete with the best subset of arms of size $M$. We design an algorithm based on a reduction to bandit submodular maximization, and show that, for $T$ rounds comprised of $N$ tasks, in the regime of large number of tasks and small number of optimal arms $M$, its regret in both settings is smaller than the simple baseline of $\\tilde{O}(\\sqrt{KNT})$ that can be obtained by using standard algorithms designed for non-stationary bandit problems. For the bandit meta-learning problem with fixed task length $\\tau$, we show that the regret of the algorithm is bounded as $\\tilde{O}(NM\\sqrt{M \\tau}+N^{2/3}M\\tau)$. Under additional assumptions on the identifiability of the optimal arms in each task, we show a bandit meta-learning algorithm with an improved $\\tilde{O}(N\\sqrt{M \\tau}+N^{1/2}\\sqrt{M K \\tau})$ regret.","url_abs":"https://arxiv.org/abs/2202.13001v6","url_pdf":"https://arxiv.org/pdf/2202.13001v6.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":"non-stationary-bandits-and-meta-learning-with","repo_url":"https://github.com/duongnhatthang/meta-bandit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.13001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.13001"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/duongnhatthang/meta-bandit","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"6fb2f5d8dd058750","entry":"plot","repo":"duongnhatthang/meta-bandit","repo_kind":"official","path":"utils.py","file_url":"https://github.com/duongnhatthang/meta-bandit/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6fb2f5d8dd058750"}},{"code_sha256_prefix":"43a72556a1715bd1","entry":"rolls_out","repo":"duongnhatthang/meta-bandit","repo_kind":"official","path":"utils.py","file_url":"https://github.com/duongnhatthang/meta-bandit/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"43a72556a1715bd1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}