I’m a first-year graduate student from Tsinghua Shenzhen International Graduate School (SIGS), Tsinghua University. I am very fortunate to be advised by Prof. Wenbo Ding. Before that, I obtained my B.Sc. degree in computational mathematics from the School of Mathematics at Southeast University, Nanjing, China, in 2024. I was honored to complete my undergraduate thesis under the supervision of Prof. Xuan Zhao.

My research lies at the intersection of Reinforcement Learning, Optimization, and Robotics. I am particularly focused on advancing sample-efficient Reinforcement Learning, with a core objective of developing principled and effective credit assignment mechanisms. My long-term vision is to significantly enhance the learning efficiency of intelligent agents, thereby enabling robust and data-efficient control for complex robotic systems.

Publications

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

Yixian Zhang , Shu’ang Yu, Tonghe Zhang, Mo Guang, Haojia Hui, Kaiwen Long, Yu Wang, Chao Yu, Wenbo Ding

Policy Newton Algorithm in Reproducing Kernel Hilbert Space

Yixian Zhang , Huaze Tang, Chao Wang, Wenbo Ding

Bidirectional Soft Actor-Critic: Leveraging Forward and Reverse KL Divergence for Efficient Reinforcement Learning

Yixian Zhang , Huaze Tang, Changxu Wei, Wenbo Ding

Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement Learning

Yixian Zhang *, Huaze Tang *, Huijing Lin, Wenbo Ding

High-dimensional Probability Preserving Scenario Reduction Method Using Adaptive Selection with Sampling for Large-scale Power System

Yixian Zhang, Yi Tang, Jiangyi Hu, Taishan Xu, Xiancheng Ren, Ren-jun Qi, Wenyu Yang, Jianru Zhang, Xuan Zhao

Deep Reinforcement Learning Using Optimized Monte Carlo Tree Search in EWN

Yixian Zhang, Zhuoxuan Li, Yiding Cao, Xuan Zhao, Jinde Cao

More publications can be viewed in my CV