{"total":36,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2111.05008","title":"Misspecified Gaussian Process Bandit Optimization","created":"2021-11-09","cited_by_count":55,"area":null},{"id":"2205.06811","title":"Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions","created":"2022-05-13","cited_by_count":51,"area":null},{"id":"2210.01898","title":"Replicable Bandits","created":"2022-10-04","cited_by_count":22,"area":null},{"id":"2102.13240","title":"Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles","created":"2021-02-26","cited_by_count":21,"area":null},{"id":"2211.05632","title":"Contexts can be Cheap: Solving Stochastic Contextual Bandits with Linear Bandit Algorithms","created":"2022-11-08","cited_by_count":19,"area":null},{"id":"2109.13595","title":"The Fragility of Optimized Bandit Algorithms","created":"2021-09-28","cited_by_count":17,"area":null},{"id":"2111.12482","title":"One More Step Towards Reality: Cooperative Bandits with Imperfect Communication","created":"2021-11-24","cited_by_count":15,"area":null},{"id":"2102.06593","title":"Pareto Optimal Model Selection in Linear Bandits","created":"2021-02-12","cited_by_count":14,"area":null},{"id":"2106.14979","title":"On component interactions in two-stage recommender systems","created":"2021-06-28","cited_by_count":14,"area":null},{"id":"2106.12034","title":"Pure Exploration in Kernel and Neural Bandits","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","cited_by_count":12,"area":null},{"id":"2310.02717","title":"Online Clustering of Bandits with Misspecified User Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2102.00490","title":"Online Markov Decision Processes with Aggregate Bandit Feedback","created":"2021-01-31","cited_by_count":10,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2502.01118","title":"Large Language Model-Enhanced Multi-Armed Bandits","created":"2025-02-03","cited_by_count":7,"area":null},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2303.09390","title":"On the Interplay Between Misspecification and Sub-optimality Gap in Linear Contextual Bandits","created":"2023-03-16","cited_by_count":6,"area":null},{"id":"2506.12751","title":"Single Index Bandits: Generalized Linear Contextual Bandits with Unknown Reward Functions","created":"2025-06-15","cited_by_count":6,"area":null},{"id":"2106.13539","title":"Dealing with Expert Bias in Collective Decision-Making","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2210.14483","title":"Robust Contextual Linear Bandits","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2310.19794","title":"Robust Causal Bandits for Linear Models","created":"2023-10-30","cited_by_count":4,"area":null},{"id":"2405.10815","title":"A Functional Model Method for Nonconvex Nonsmooth Conditional Stochastic Optimization","created":"2024-05-17","cited_by_count":4,"area":null},{"id":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2605.26156","title":"Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges","created":"2026-05-24","cited_by_count":4,"area":null},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2302.13252","title":"No-Regret Linear Bandits beyond Realizability","created":"2023-02-26","cited_by_count":2,"area":null},{"id":"2309.16563","title":"CRIMED: Lower and Upper Bounds on Regret for Bandits with Unbounded Stochastic Corruption","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2405.07795","title":"Improved Bound for Robust Causal Bandits with Linear Models","created":"2024-05-13","cited_by_count":2,"area":null},{"id":"2107.05849","title":"Model Selection for Generic Reinforcement Learning","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2207.02992","title":"Model Selection in Reinforcement Learning with General Function Approximations","created":"2022-07-06","cited_by_count":1,"area":null},{"id":"2605.09454","title":"Optimal Regret for Single Index Bandits","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2606.14929","title":"Policy Regret for Embedding Model Routing: Contextual Bandits with Low-Rank Experts","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2208.09819","title":"Robust Tests in Online Decision-Making","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2509.01924","title":"Non-Linear Model-Based Sequential Decision-Making in Agriculture","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2609.35622","title":"Elicitation and Decision Geometry in Single-Index Bandits","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}