CV

M.Sc.

Nanjing University, Nanjing, China

• LAMDA Group, School of Artificial Intelligence
• Supervisor: Prof. Yang Yu

B.Sc.

Sichuan University, Chengdu, China

• Software Enginering in School of Software

Model-Bellman inconsistency for model-based offline reinforcement learning

Yihao Sun*, Jiaji Zhang*, Chengxing Jia, Haoxin Lin, Junyin Ye, Yang Yu

ICML'23

Model-based reinforcement learning with multi-step plan value estimation

Haoxin Lin*, Yihao Sun*, Jiaji Zhang, Yang Yu

ECAI'23

Episodic return decomposition by difference of implicitly assigned sub-trajectory reward

Haoxin Lin, Hongqiu Wu, Jiaji Zhang, Yihao Sun, Junyin Ye, Yang Yu

AAAI'24

Flow to better, Offline preference-based reinforcement learning via preferred trajectory generation

Zhilong Zhang*, Yihao Sun*, Junyin Ye, Tianshou Liu, Jiaji Zhang, Yang Yu

ICLR'24

OfflineRL-Kit

• An elegant PyTorch offline reinforcement learning library.

• Xiaomi Outstanding Scholarship (10 recipients schoolwide).

• The First Class Academic Scholarship in Nanjing University.