{"total":35,"rows":[{"id":"2107.05745","title":"Adapting to Misspecification in Contextual Bandits","created":"2021-07-12","cited_by_count":81,"area":null},{"id":"2107.02237","title":"Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination","created":"2021-07-05","cited_by_count":53,"area":null},{"id":"2207.05836","title":"Contextual Bandits with Large Action Spaces: Made Practical","created":"2022-07-12","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"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":"2309.00814","title":"Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits","created":"2023-09-02","cited_by_count":19,"area":null},{"id":"2207.05849","title":"Contextual Bandits with Smooth Regret: Efficient Learning in Continuous Action Spaces","created":"2022-07-12","cited_by_count":18,"area":null},{"id":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"area":null},{"id":"2207.11126","title":"Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP","created":"2022-07-22","cited_by_count":11,"area":null},{"id":"2211.14932","title":"Eluder-based Regret for Stochastic Contextual MDPs","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2303.01464","title":"Efficient Rate Optimal Regret for Adversarial Contextual MDPs Using Online Function Approximation","created":"2023-03-02","cited_by_count":9,"area":null},{"id":"2410.12713","title":"How Does Variance Shape the Regret in Contextual Bandits?","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2405.17796","title":"Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"area":null},{"id":"2510.09127","title":"Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2310.05047","title":"Online Learning in Contextual Second-Price Pay-Per-Click Auctions","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2402.08126","title":"Contextual Multinomial Logit Bandits with General Value Functions","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2602.09456","title":"Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2501.14155","title":"Learning to Price with Resource Constraints: From Full Information to Machine-Learned Prices","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2302.08551","title":"Infinite Action Contextual Bandits with Reusable Data Exhaust","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2404.09413","title":"On the Optimal Regret of Locally Private Linear Contextual Bandit","created":"2024-04-15","cited_by_count":2,"area":null},{"id":"2602.13700","title":"Optimal Regret for Policy Optimization in Contextual Bandits","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2602.13706","title":"Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation","created":"2026-02-14","cited_by_count":2,"area":null},{"id":"2312.16341","title":"Harnessing the Power of Federated Learning in Federated Contextual Bandits","created":"2023-12-26","cited_by_count":1,"area":null},{"id":"2505.07101","title":"Constrained Online Decision-Making: A Unified Framework","created":"2025-05-11","cited_by_count":1,"area":null},{"id":"2604.18912","title":"Collaborative Contextual Bayesian Optimization","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2607.13686","title":"Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2609.13564","title":"When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2111.05232","title":"Learning Rates for Nonconvex Pairwise Learning","created":"2021-11-09","cited_by_count":0,"area":null},{"id":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","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":"2603.24974","title":"The Value of Information in Resource-Constrained Pricing","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2607.28408","title":"On-Policy and Off-Policy Learning for Large Action Spaces","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2609.33888","title":"Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.19804","title":"Efficient contextual partial monitoring with general function approximation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}