I am a postdoc research fellow at the University of Michigan, Ann Arbor.

News

[Oct-2025] I will attend INFORMS Annual Meeting 2025 in Atlanta and present our work "Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets". Section: Learning, Ranking, and Selection. Oct 26 (Sunday), 2:45-4:00 pm, Building A Level 3 A315.

[Jul-2025] I will attend INFORMS APS Conference 2025 in Atlanta. I will present two works:

"Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets". Session: Recent Advances in Stochastic Matching Networks, Jul 1 (Tuesday), 10:30 am-12 pm, Instruction Center (IC) Classroom 211.

"Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB". Session: Nonasymptotic Limit Theorems and Finite-Time Bounds in Machine Learning, Jul 2 (Wednesday), 10:30 am-12 pm, Georgia Tech Exhibition: Buckhead.

Selected Publications

[1] Zixian Yang, R. Srikant, and Lei Ying, “Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB,” in Proc. 26th International Conference on Artificial Intelligence and Statistics (acceptance rate 29%), PMLR 206:4275-4312, 2023. link of the paper

[2] Zixian Yang, Xin Liu, and Lei Ying. "Exploration. Exploitation, and Engagement in Multi-Armed Bandits with Abandonment." Journal of Machine Learning Research, 2024. link of the paper

[3] Honghao Wei, Zixian Yang, Xin Liu, Zhiwei Qin, Xiaocheng Tang, and Lei Ying. "A Reinforcement Learning and Prediction-Based Lookahead Policy for Vehicle Repositioning in Online Ride-Hailing Systems." IEEE Transactions on Intelligent Transportation Systems, 2023. link of the paper

[4] Xin Liu, Zixian Yang, and Lei Ying, “Online Nonstochastic Control with Adversarial and Static Constraints,” in Proc. 40th International Conference on Machine Learning (acceptance rate 28%), PMLR 202:22277-22288, 2023. link of the paper

Preprints

[1] Zixian Yang and Lei Ying, “Learning-Based Pricing and Matching for Two-Sided Queues,” 2024, available at https://arxiv.org/abs/2403.11093v2

[2] Zixian Yang, R. Srikant, and Lei Ying, “Learning While Scheduling in Multi-Server Systems with Unknown Statistics: MaxWeight with Discounted UCB,” 2023, available at https://arxiv.org/abs/2209.01126v3

Book

Zixian Yang and Lei Ying, Introduction to Reinforcement Learning. The book is available here. The code is available here.

It is an introductory book on reinforcement learning, featuring examples and code demonstrations.