RZHU.GITHUB.IO
Updated 488 days ago
Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing (with Jingwei Ji and Renyuan Xu) Preprint ◇ Preliminary version: Proceedings of the 3rd ACM International Conference on AI in Finance (ICAIF 2022), INFORMS Workshop on Data Science 2022...
Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control (with Weichao Mao, Kaiqing Zhang, David Simchi-Levi, and Tamer Basar) Reject & Resubmit, Management Science ◇ Preliminary version: Proceedings of the 38th International Conference on Machine Learning (ICML 2021)...
I work on developing novel algorithms for machine learning and sequential decision-making (e.g., multi-armed bandits and reinforcement learning) to address fundamental and practical challenges in revenue management, supply chain, and service operations.