{"total":19,"rows":[{"id":"2202.04593","title":"Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models","created":"2022-02-09","cited_by_count":37,"area":null},{"id":"2202.05567","title":"Shuffle Private Linear Contextual Bandits","created":"2022-02-11","cited_by_count":27,"area":null},{"id":"2203.15589","title":"On Kernelized Multi-Armed Bandits with Constraints","created":"2022-03-29","cited_by_count":23,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2206.05772","title":"Distributed Differential Privacy in Multi-Armed Bandits","created":"2022-06-12","cited_by_count":14,"area":null},{"id":"2302.13945","title":"On Differentially Private Federated Linear Contextual Bandits","created":"2023-02-27","cited_by_count":14,"area":null},{"id":"2502.08870","title":"When and why randomised exploration works (in linear bandits)","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2109.06234","title":"Machine Learning for Online Algorithm Selection under Censored Feedback","created":"2021-09-13","cited_by_count":3,"area":null},{"id":"2402.05002","title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2506.01250","title":"Neural Variance-aware Dueling Bandits with Deep Representation and Shallow Exploration","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2205.03820","title":"Some performance considerations when using multi-armed bandit algorithms in the presence of missing data","created":"2022-05-08","cited_by_count":1,"area":null},{"id":"2402.09456","title":"Optimistic Thompson Sampling for No-Regret Learning in Unknown Games","created":"2024-02-07","cited_by_count":1,"area":null},{"id":"2307.03587","title":"Weighted Sequential Bayesian Inference for Non-Stationary Linear Contextual Bandits","created":"2023-07-07","cited_by_count":0,"area":null},{"id":"2510.17390","title":"Exploration via Feature Perturbation in Contextual Bandits","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.05019","title":"A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2606.28616","title":"Randomized Exploration for Linear Bandits via Absolute Perturbations","created":"2026-06-26","cited_by_count":0,"area":null}],"next_cursor":null}