{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/multi-armed-bandits/papers/13","list_of":"/task/multi-armed-bandits","task":"Multi-Armed Bandits","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":13,"rows_per_page":100,"rows":[1201,1262],"of":1262,"counts":{"archive_papers_tagged":1262,"with_a_code_link":253,"where_syntology_ran_a_sample":55,"not_listed_spam_title":0,"listed":1262,"listed_where_code_ran":55,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":44,"every_run_a_failure_of_syntologys_instrument":11,"listed_with_a_run_with_no_instrument_failure":44,"listed_every_run_a_failure_of_syntologys_instrument":11,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/multi-armed-bandits","prev":"/task/multi-armed-bandits/papers/12","next":null,"papers":[{"url":null,"slug":"personalized-course-sequence-recommendations","title":"Personalized Course Sequence Recommendations","date":"2015-12-30","arxiv_id":"1512.09176","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-top-k-selection-in-multi-armed-bandits-and","title":"On Top-k Selection in Multi-Armed Bandits and Hidden Bipartite Graphs","date":"2015-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-differentially-private-multi","title":"Algorithms for Differentially Private Multi-Armed Bandits","date":"2015-11-27","arxiv_id":"1511.08681","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-analysis-of-the-finite-horizon-gittins","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","date":"2015-11-18","arxiv_id":"1511.06014","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-aware-bandits","title":"Context-Aware Bandits","date":"2015-10-12","arxiv_id":"1510.03164","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-application-to-5g","title":"Multi-armed Bandits with Application to 5G Small Cells","date":"2015-10-02","arxiv_id":"1510.00627","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-design-for-ranking-response","title":"Sequential Design for Ranking Response Surfaces","date":"2015-09-03","arxiv_id":"1509.00980","repositories_listed":0,"syntology":null},{"url":null,"slug":"episodic-multi-armed-bandits","title":"Episodic Multi-armed Bandits","date":"2015-08-04","arxiv_id":"1508.00641","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-contextual-bandits-with-knapsacks","title":"Linear Contextual Bandits with Knapsacks","date":"2015-07-24","arxiv_id":"1507.06738","repositories_listed":0,"syntology":null},{"url":null,"slug":"selecting-the-best-system-and-multi-armed","title":"Selecting the best system and multi-armed bandits","date":"2015-07-16","arxiv_id":"1507.04564","repositories_listed":0,"syntology":null},{"url":null,"slug":"upper-confidence-bound-algorithms-for-active","title":"Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits","date":"2015-07-16","arxiv_id":"1507.04523","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-discrete-sampling-as-a-multi-armed","title":"Scalable Discrete Sampling as a Multi-Armed Bandit Problem","date":"2015-06-30","arxiv_id":"1506.09039","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-algorithm-for-contextual-bandits","title":"An efficient algorithm for contextual bandits with knapsacks, and an extension to concave objectives","date":"2015-06-10","arxiv_id":"1506.03374","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-regret-optimal-learning-in-decentralized","title":"On Regret-Optimal Learning in Decentralized Multi-player Multi-armed Bandits","date":"2015-05-04","arxiv_id":"1505.00553","repositories_listed":0,"syntology":null},{"url":null,"slug":"thompson-sampling-for-budgeted-multi-armed","title":"Thompson Sampling for Budgeted Multi-armed Bandits","date":"2015-05-01","arxiv_id":"1505.00146","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-with-logarithmic-or-sublinear","title":"Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits","date":"2015-04-27","arxiv_id":"1504.06937","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-vs-communication-distributed","title":"Regret vs. Communication: Distributed Stochastic Multi-Armed Bandits and Beyond","date":"2015-04-14","arxiv_id":"1504.03509","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-bandits","title":"Global Bandits","date":"2015-03-29","arxiv_id":"1503.08370","repositories_listed":0,"syntology":null},{"url":null,"slug":"networked-stochastic-multi-armed-bandits-with","title":"Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies","date":"2015-03-20","arxiv_id":"1503.06169","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-search-better-than-your-teacher","title":"Learning to Search Better Than Your Teacher","date":"2015-02-08","arxiv_id":"1502.02206","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-pure-exploration-of-multi-armed","title":"Combinatorial Pure Exploration of Multi-Armed Bandits","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multiple-tasks-in-parallel-with-a","title":"Learning Multiple Tasks in Parallel with a Shared Annotator","date":"2014-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nonstochastic-multi-armed-bandits-with-graph","title":"Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback","date":"2014-09-30","arxiv_id":"1409.8428","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-minimax-optimal-offline-policy-evaluation","title":"On Minimax Optimal Offline Policy Evaluation","date":"2014-09-12","arxiv_id":"1409.3653","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-warm-up-cold-recommender-systems","title":"Bandits Warm-up Cold Recommender Systems","date":"2014-07-10","arxiv_id":"1407.2806","repositories_listed":0,"syntology":null},{"url":null,"slug":"unimodal-bandits-regret-lower-bounds-and","title":"Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms","date":"2014-05-20","arxiv_id":"1405.5096","repositories_listed":0,"syntology":null},{"url":null,"slug":"lipschitz-bandits-regret-lower-bounds-and","title":"Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithms","date":"2014-05-19","arxiv_id":"1405.4758","repositories_listed":0,"syntology":null},{"url":null,"slug":"reducing-dueling-bandits-to-cardinal-bandits","title":"Reducing Dueling Bandits to Cardinal Bandits","date":"2014-05-14","arxiv_id":"1405.3396","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-contract-design-for-crowdsourcing","title":"Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems","date":"2014-05-12","arxiv_id":"1405.2875","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-risk-aversion-in-stochastic-multi","title":"Generalized Risk-Aversion in Stochastic Multi-Armed Bandits","date":"2014-05-05","arxiv_id":"1405.0833","repositories_listed":0,"syntology":null},{"url":null,"slug":"resourceful-contextual-bandits","title":"Resourceful Contextual Bandits","date":"2014-02-27","arxiv_id":"1402.6779","repositories_listed":0,"syntology":null},{"url":null,"slug":"algorithms-for-multi-armed-bandit-problems","title":"Algorithms for multi-armed bandit problems","date":"2014-02-25","arxiv_id":"1402.6028","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploration-vs-exploitation-vs-safety-risk","title":"Exploration vs Exploitation vs Safety: Risk-averse Multi-Armed Bandits","date":"2014-01-06","arxiv_id":"1401.1123","repositories_listed":0,"syntology":null},{"url":null,"slug":"lil-ucb-an-optimal-exploration-algorithm-for","title":"lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits","date":"2013-12-27","arxiv_id":"1312.7308","repositories_listed":0,"syntology":null},{"url":null,"slug":"fundamental-limits-of-online-and-distributed","title":"Fundamental Limits of Online and Distributed Algorithms for Statistical Learning and Estimation","date":"2013-11-14","arxiv_id":"1311.3494","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-exploration-in-multi-armed","title":"Distributed Exploration in Multi-Armed Bandits","date":"2013-11-04","arxiv_id":"1311.0800","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-thompson-sampling-for-contextual","title":"Generalized Thompson Sampling for Contextual Bandits","date":"2013-10-27","arxiv_id":"1310.7163","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-for-intelligent-tutoring","title":"Multi-Armed Bandits for Intelligent Tutoring Systems","date":"2013-10-11","arxiv_id":"1310.3174","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-monte-carlo-bandits","title":"Sequential Monte Carlo Bandits","date":"2013-10-04","arxiv_id":"1310.1404","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-bridges-viewing-active-learning-from","title":"Building Bridges: Viewing Active Learning from the Multi-Armed Bandit Lens","date":"2013-09-26","arxiv_id":"1309.6830","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-analysis-of-kernelised-contextual","title":"Finite-Time Analysis of Kernelised Contextual Bandits","date":"2013-09-26","arxiv_id":"1309.6869","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-online-learning-via-cooperative","title":"Distributed Online Learning via Cooperative Contextual Bandits","date":"2013-08-21","arxiv_id":"1308.4568","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-human-decision-making-in-generalized","title":"Modeling Human Decision-making in Generalized Gaussian Multi-armed Bandits","date":"2013-07-23","arxiv_id":"1307.6134","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-distribution-free-multi-armed-bandits","title":"Towards Distribution-Free Multi-Armed Bandits with Combinatorial Strategies","date":"2013-07-20","arxiv_id":"1307.5438","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-bandits-to-experts-a-tale-of-domination","title":"From Bandits to Experts: A Tale of Domination and Independence","date":"2013-07-17","arxiv_id":"1307.4564","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-finding-the-largest-mean-among-many","title":"On Finding the Largest Mean Among Many","date":"2013-06-17","arxiv_id":"1306.3917","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-approximation-for-speeding-up-lstd","title":"Concentration bounds for temporal difference learning with linear function approximation: The case of batch data and uniform sampling","date":"2013-06-11","arxiv_id":"1306.2557","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-gang-of-bandits","title":"A Gang of Bandits","date":"2013-06-04","arxiv_id":"1306.0811","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-ad-allocation-bandits-with-budgets","title":"Dynamic Ad Allocation: Bandits with Budgets","date":"2013-06-01","arxiv_id":"1306.0155","repositories_listed":0,"syntology":null},{"url":null,"slug":"exponentiated-gradient-linucb-for-contextual","title":"Exponentiated Gradient LINUCB for Contextual Multi-Armed Bandits","date":"2013-05-10","arxiv_id":"1305.2415","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-optimistic-region-selection","title":"Hierarchical Optimistic Region Selection driven by Curiosity","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-aversion-in-multi-armed-bandits","title":"Risk-Aversion in Multi-armed Bandits","date":"2012-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-evaluation-of-thompson-sampling","title":"An Empirical Evaluation of Thompson Sampling","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-bandits-to-experts-on-the-value-of-side","title":"From Bandits to Experts: On the Value of Side-Observations","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-on-implicit-metric-spaces","title":"Multi-armed bandits on implicit metric spaces","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"pac-bayesian-analysis-of-contextual-bandits","title":"PAC-Bayesian Analysis of Contextual Bandits","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-pricing-with-limited-supply","title":"Dynamic Pricing with Limited Supply","date":"2011-08-20","arxiv_id":"1108.4142","repositories_listed":0,"syntology":null},{"url":null,"slug":"combinatorial-network-optimization-with","title":"Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards","date":"2010-11-22","arxiv_id":"1011.4748","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-with-similarity","title":"Contextual Bandits with Similarity Information","date":"2009-07-23","arxiv_id":"0907.3986","repositories_listed":0,"syntology":null},{"url":null,"slug":"mortal-multi-armed-bandits","title":"Mortal Multi-Armed Bandits","date":"2008-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-diverse-rankings-with-multi-armed","title":"Learning diverse rankings with multi-armed bandits","date":"2008-07-05","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-epoch-greedy-algorithm-for-multi-armed","title":"The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information","date":"2007-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"813057cb9c2c89c3de69e4fd8f19474899bcd9d71c15254c6480ae46aef16e8f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}