John C. S. Lui

5

Papers

22

Total Citations

Papers (5)

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users

Federated In-Context Learning: Iterative Refinement for Improved Answer Quality

Fusing Reward and Dueling Feedback in Stochastic Bandits

Online Clustering of Dueling Bandits