{"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/8","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":8,"pages_in_order":13,"rows_per_page":100,"rows":[701,800],"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/7","next":"/task/multi-armed-bandits/papers/9","papers":[{"url":null,"slug":"breaking-the-sqrt-t-barrier-instance","title":"Breaking the $\\sqrt{T}$ Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits","date":"2022-05-19","arxiv_id":"2205.09899","repositories_listed":0,"syntology":null},{"url":null,"slug":"slowly-changing-adversarial-bandit-algorithms","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","date":"2022-05-18","arxiv_id":"2205.09056","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-parametric-contextual-bandits-with-graph","title":"Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization","date":"2022-05-17","arxiv_id":"2205.08295","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-dirichlet-to-rubin-optimistic","title":"From Dirichlet to Rubin: Optimistic Exploration in RL without Bonuses","date":"2022-05-16","arxiv_id":"2205.07704","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-optimal-algorithms-for-linear","title":"Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions","date":"2022-05-13","arxiv_id":"2205.06811","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-risk-aware-multi-armed-bandits","title":"A Survey of Risk-Aware Multi-Armed Bandits","date":"2022-05-12","arxiv_id":"2205.05843","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-multi-armed-bandits-under-byzantine","title":"Federated Multi-Armed Bandits Under Byzantine Attacks","date":"2022-05-09","arxiv_id":"2205.04134","repositories_listed":0,"syntology":null},{"url":null,"slug":"selectively-contextual-bandits","title":"Selectively Contextual Bandits","date":"2022-05-09","arxiv_id":"2205.04528","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-player-multi-armed-bandits-with-finite","title":"Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications","date":"2022-04-28","arxiv_id":"2204.13502","repositories_listed":0,"syntology":null},{"url":null,"slug":"rate-constrained-remote-contextual-bandits","title":"Rate-Constrained Remote Contextual Bandits","date":"2022-04-26","arxiv_id":"2204.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"worst-case-performance-of-greedy-policies-in","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","date":"2022-04-10","arxiv_id":"2204.04773","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-multi-armed-bandits-with-non","title":"Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System","date":"2022-04-06","arxiv_id":"2204.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"strategies-for-safe-multi-armed-bandits-with","title":"Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk","date":"2022-04-01","arxiv_id":"2204.00706","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexible-and-efficient-contextual-bandits","title":"Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles","date":"2022-03-30","arxiv_id":"2203.16668","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-in-restless-markov","title":"Best Arm Identification in Restless Markov Multi-Armed Bandits","date":"2022-03-29","arxiv_id":"2203.15236","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-kernelized-multi-armed-bandits-with","title":"On Kernelized Multi-Armed Bandits with Constraints","date":"2022-03-29","arxiv_id":"2203.15589","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-attrition-in-recommender-systems","title":"Modeling Attrition in Recommender Systems with Departing Bandits","date":"2022-03-25","arxiv_id":"2203.13423","repositories_listed":0,"syntology":null},{"url":null,"slug":"approximate-function-evaluation-via-multi","title":"Approximate Function Evaluation via Multi-Armed Bandits","date":"2022-03-18","arxiv_id":"2203.10124","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-meta-active-learning","title":"Reinforced Meta Active Learning","date":"2022-03-09","arxiv_id":"2203.04573","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-contextual-bandits-via-reward-biased","title":"Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits","date":"2022-03-08","arxiv_id":"2203.04192","repositories_listed":0,"syntology":null},{"url":null,"slug":"pac-bayesian-lifelong-learning-for-multi","title":"PAC-Bayesian Lifelong Learning For Multi-Armed Bandits","date":"2022-03-07","arxiv_id":"2203.03303","repositories_listed":0,"syntology":null},{"url":null,"slug":"restless-multi-armed-bandits-under-exogenous","title":"Restless Multi-Armed Bandits under Exogenous Global Markov Process","date":"2022-02-28","arxiv_id":"2202.13665","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-online-sparse-decision-making","title":"Federated Online Sparse Decision Making","date":"2022-02-27","arxiv_id":"2202.13448","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pareto-frontier-of-instance-dependent","title":"The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication","date":"2022-02-19","arxiv_id":"2202.09653","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-distributed-machine-learning-via","title":"Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits","date":"2022-02-16","arxiv_id":"2202.08302","repositories_listed":0,"syntology":null},{"url":null,"slug":"versatile-dueling-bandits-best-of-both-world","title":"Versatile Dueling Bandits: Best-of-both-World Analyses for Online Learning from Preferences","date":"2022-02-14","arxiv_id":"2202.06694","repositories_listed":0,"syntology":null},{"url":null,"slug":"shuffle-private-linear-contextual-bandits","title":"Shuffle Private Linear Contextual Bandits","date":"2022-02-11","arxiv_id":"2202.05567","repositories_listed":0,"syntology":null},{"url":null,"slug":"remote-contextual-bandits","title":"Remote Contextual Bandits","date":"2022-02-10","arxiv_id":"2202.05182","repositories_listed":0,"syntology":null},{"url":null,"slug":"settling-the-communication-complexity-for","title":"Settling the Communication Complexity for Distributed Offline Reinforcement Learning","date":"2022-02-10","arxiv_id":"2202.04862","repositories_listed":0,"syntology":null},{"url":null,"slug":"smoothed-online-learning-is-as-easy-as","title":"Smoothed Online Learning is as Easy as Statistical Learning","date":"2022-02-09","arxiv_id":"2202.04690","repositories_listed":0,"syntology":null},{"url":null,"slug":"budgeted-combinatorial-multi-armed-bandits","title":"Budgeted Combinatorial Multi-Armed Bandits","date":"2022-02-08","arxiv_id":"2202.03704","repositories_listed":0,"syntology":null},{"url":null,"slug":"variance-optimal-augmentation-logging-for","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","date":"2022-02-03","arxiv_id":"2202.01721","repositories_listed":0,"syntology":null},{"url":null,"slug":"decision-focused-learning-in-restless-multi","title":"Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health","date":"2022-02-02","arxiv_id":"2202.00916","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-algorithms-for-learning-to-control","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","date":"2022-02-02","arxiv_id":"2202.00867","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-for-link-configuration-in","title":"Multi-armed Bandits for Link Configuration in Millimeter-wave Networks","date":"2022-02-02","arxiv_id":"2202.01196","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-uncertainty-in-contextual-bandits","title":"Context Uncertainty in Contextual Bandits with Applications to Recommender Systems","date":"2022-02-01","arxiv_id":"2202.00805","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-collaborative-filtering-bandits-via","title":"Neural Collaborative Filtering Bandits via Meta Learning","date":"2022-01-31","arxiv_id":"2201.13395","repositories_listed":0,"syntology":null},{"url":null,"slug":"coordinated-attacks-against-contextual","title":"Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms","date":"2022-01-30","arxiv_id":"2201.12700","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-best-of-both-worlds-algorithm-for","title":"Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits","date":"2022-01-28","arxiv_id":"2201.11921","repositories_listed":0,"syntology":null},{"url":null,"slug":"networked-restless-multi-armed-bandits-for","title":"Networked Restless Multi-Armed Bandits for Mobile Interventions","date":"2022-01-28","arxiv_id":"2201.12408","repositories_listed":0,"syntology":null},{"url":null,"slug":"top-k-ranking-deep-contextual-bandits-for","title":"Top-K Ranking Deep Contextual Bandits for Information Selection Systems","date":"2022-01-28","arxiv_id":"2201.13287","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-contextual-bandits-through-perturbed","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","date":"2022-01-24","arxiv_id":"2201.09910","repositories_listed":0,"syntology":null},{"url":null,"slug":"occupancy-information-ratio-infinite-horizon","title":"Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search","date":"2022-01-21","arxiv_id":"2201.08832","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-parsing-for-planning-goals-as","title":"Semantic Parsing for Planning Goals as Constrained Combinatorial Contextual Bandits","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandits-for-advertising-campaigns","title":"Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version)","date":"2022-01-13","arxiv_id":"2201.05231","repositories_listed":0,"syntology":null},{"url":null,"slug":"modelling-cournot-games-as-multi-agent-multi","title":"Modelling Cournot Games as Multi-agent Multi-armed Bandits","date":"2022-01-01","arxiv_id":"2201.01182","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-linear-leveling-bandits","title":"Safe Linear Leveling Bandits","date":"2021-12-13","arxiv_id":"2112.06728","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochastic-differential-equations-for-1","title":"Stochastic differential equations for limiting description of UCB rule for Gaussian multi-armed bandits","date":"2021-12-13","arxiv_id":"2112.06423","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-amplification-via-shuffling-for","title":"Privacy Amplification via Shuffling for Linear Contextual Bandits","date":"2021-12-11","arxiv_id":"2112.06008","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-action-poisoning-attacks-on-linear","title":"Efficient Action Poisoning Attacks on Linear Contextual Bandits","date":"2021-12-10","arxiv_id":"2112.05367","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-under-additive","title":"Best Arm Identification under Additive Transfer Bandits","date":"2021-12-08","arxiv_id":"2112.04083","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-bandit-applications-in-customer","title":"Contextual Bandit Applications in Customer Support Bot","date":"2021-12-06","arxiv_id":"2112.03210","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-submodular-contextual-bandits","title":"On Submodular Contextual Bandits","date":"2021-12-03","arxiv_id":"2112.02165","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotically-best-causal-effect","title":"Asymptotically Best Causal Effect Identification with Multi-Armed Bandits","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-with-knapsacks-beyond-the-worst-case","title":"Bandits with Knapsacks beyond the Worst Case","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-armed-bandits-with-bounded-arm-memory","title":"Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-algorithms-for-stochastic-contextual","title":"Optimal Algorithms for Stochastic Contextual Preference Bandits","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"online-fair-revenue-maximizing-cake-division","title":"Online Fair Revenue Maximizing Cake Division with Non-Contiguous Pieces in Adversarial Bandits","date":"2021-11-29","arxiv_id":"2111.14387","repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-multi-armed-bandit-can","title":"Decentralized Upper Confidence Bound Algorithms for Homogeneous Multi-Agent Multi-Armed Bandits","date":"2021-11-22","arxiv_id":"2111.10933","repositories_listed":0,"syntology":null},{"url":null,"slug":"offline-contextual-bandits-for-wireless","title":"Offline Contextual Bandits for Wireless Network Optimization","date":"2021-11-11","arxiv_id":"2111.08587","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-instance-dependent-analysis-for-the","title":"An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit","date":"2021-11-08","arxiv_id":"2111.04873","repositories_listed":0,"syntology":null},{"url":null,"slug":"universal-and-data-adaptive-algorithms-for","title":"Universal and data-adaptive algorithms for model selection in linear contextual bandits","date":"2021-11-08","arxiv_id":"2111.04688","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-communication-efficient","title":"Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits","date":"2021-11-02","arxiv_id":"2111.01570","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-dont-follow-rules-balancing-multi","title":"Bandits Don’t Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decentralized-cooperative-reinforcement","title":"Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure","date":"2021-11-01","arxiv_id":"2111.00781","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-linear-contextual-bandits","title":"Federated Linear Contextual Bandits","date":"2021-10-27","arxiv_id":"2110.14177","repositories_listed":0,"syntology":null},{"url":null,"slug":"linear-contextual-bandits-with-adversarial","title":"Linear Contextual Bandits with Adversarial Corruptions","date":"2021-10-25","arxiv_id":"2110.12615","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pareto-frontier-of-model-selection-for","title":"The Pareto Frontier of model selection for general Contextual Bandits","date":"2021-10-25","arxiv_id":"2110.13282","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-thompson-sampling-for-partially","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","date":"2021-10-23","arxiv_id":"2110.12175","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-pricing-and-assortment-under-a","title":"Dynamic pricing and assortment under a contextual MNL demand","date":"2021-10-19","arxiv_id":"2110.10018","repositories_listed":0,"syntology":null},{"url":null,"slug":"stateful-offline-contextual-policy-evaluation","title":"Stateful Offline Contextual Policy Evaluation and Learning","date":"2021-10-19","arxiv_id":"2110.10081","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-pareto-frontier-of-regret-minimization","title":"Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits","date":"2021-10-16","arxiv_id":"2110.08627","repositories_listed":0,"syntology":null},{"url":null,"slug":"almost-optimal-batch-regret-tradeoff-for","title":"Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits","date":"2021-10-15","arxiv_id":"2110.08057","repositories_listed":0,"syntology":null},{"url":null,"slug":"bandits-don-t-follow-rules-balancing-multi","title":"Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Bandits","date":"2021-10-13","arxiv_id":"2110.06997","repositories_listed":0,"syntology":null},{"url":null,"slug":"dare-not-to-ask-problem-dependent-guarantees","title":"Query-Reward Tradeoffs in Multi-Armed Bandits","date":"2021-10-12","arxiv_id":"2110.05724","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-upper-confidence-bound-algorithm-for","title":"Deep Upper Confidence Bound Algorithm for Contextual Bandit Ranking of Information Selection","date":"2021-10-08","arxiv_id":"2110.04127","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-selection-approach-for-corruption","title":"A Model Selection Approach for Corruption Robust Reinforcement Learning","date":"2021-10-07","arxiv_id":"2110.03580","repositories_listed":0,"syntology":null},{"url":null,"slug":"feel-good-thompson-sampling-for-contextual","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","date":"2021-10-02","arxiv_id":"2110.00871","repositories_listed":0,"syntology":null},{"url":null,"slug":"asymptotic-performance-of-thompson-sampling","title":"Asymptotic Performance of Thompson Sampling in the Batched Multi-Armed Bandits","date":"2021-10-01","arxiv_id":"2110.00158","repositories_listed":0,"syntology":null},{"url":null,"slug":"batched-thompson-sampling","title":"Batched Thompson Sampling","date":"2021-10-01","arxiv_id":"2110.00202","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-bandit-algorithms-for-settings-with","title":"Adapting Bandit Algorithms for Settings with Sequentially Available Arms","date":"2021-09-30","arxiv_id":"2109.15228","repositories_listed":0,"syntology":null},{"url":null,"slug":"batched-bandits-with-crowd-externalities","title":"Batched Bandits with Crowd Externalities","date":"2021-09-29","arxiv_id":"2109.14733","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-contextual-bandits-with-targeted","title":"Causal Contextual Bandits with Targeted Interventions","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"expected-improvement-based-contextual-bandits","title":"Expected Improvement-based Contextual Bandits","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-ofu-an-efficient-algorithm-for","title":"Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"risk-averse-non-stationary-multi-armed","title":"Risk averse non-stationary multi-armed bandits","date":"2021-09-28","arxiv_id":"2109.13977","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-generalization-of-quadratic-neural","title":"Robust Generalization of Quadratic Neural Networks via Function Identification","date":"2021-09-22","arxiv_id":"2109.10935","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-translation-and-scale-invariant","title":"Generalized Translation and Scale Invariant Online Algorithm for Adversarial Multi-Armed Bandits","date":"2021-09-19","arxiv_id":"2109.09212","repositories_listed":0,"syntology":null},{"url":null,"slug":"field-study-in-deploying-restless-multi-armed","title":"Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health","date":"2021-09-16","arxiv_id":"2109.08075","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-federated-best-arm-identification-in","title":"Exploiting Heterogeneity in Robust Federated Best-Arm Identification","date":"2021-09-13","arxiv_id":"2109.05700","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-algorithms-for-misspecified-linear","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","date":"2021-09-12","arxiv_id":"2109.05546","repositories_listed":0,"syntology":null},{"url":null,"slug":"best-arm-identification-in-correlated-multi","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","date":"2021-09-10","arxiv_id":"2109.04941","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-learning-for-cooperative-multi-player","title":"Online Learning for Cooperative Multi-Player Multi-Armed Bandits","date":"2021-09-07","arxiv_id":"2109.03818","repositories_listed":0,"syntology":null},{"url":null,"slug":"max-utility-based-arm-selection-strategy-for","title":"Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations","date":"2021-08-31","arxiv_id":"2108.13810","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-dba-no-regret-multi-armed-bandits-for","title":"No DBA? No regret! Multi-armed bandits for index tuning of analytical and HTAP workloads with provable guarantees","date":"2021-08-23","arxiv_id":"2108.10130","repositories_listed":0,"syntology":null},{"url":null,"slug":"batched-thompson-sampling-for-multi-armed","title":"Batched Thompson Sampling for Multi-Armed Bandits","date":"2021-08-15","arxiv_id":"2108.06812","repositories_listed":0,"syntology":null},{"url":null,"slug":"metadata-based-multi-task-bandits-with","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","date":"2021-08-13","arxiv_id":"2108.06422","repositories_listed":0,"syntology":null},{"url":null,"slug":"regret-analysis-of-learning-based-mpc-with","title":"Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function","date":"2021-08-04","arxiv_id":"2108.02307","repositories_listed":0,"syntology":null},{"url":null,"slug":"indexability-and-rollout-policy-for-multi","title":"Indexability and Rollout Policy for Multi-State Partially Observable Restless Bandits","date":"2021-07-30","arxiv_id":"2108.00892","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-online-learning-and-offline","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","date":"2021-07-24","arxiv_id":"2107.11533","repositories_listed":0,"syntology":null}],"record_sha256":"d4c04c0830788bb51a216d75c9b0b8aa7d660004373c2c15931a7e42f6b7d33c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}