Wenzhe Li

Princeton University

My name is Wenzhe Li (李文哲). I am a Ph.D. student in the Department of Electrical and Computer Engineering at Princeton University, advised by Chi Jin. I received my B.E. from the Department of Computer Science and Technology at Tsinghua University, where I was fortunate to work with Chongjie Zhang, Guy Van den Broeck, and Stefano Ermon.

My research interests lie in reinforcement learning and probabilistic methods for machine learning. I have worked on topics including offline reinforcement learning, score-based generative models, and approximate inference.

Interests

Reinforcement Learning
Offline Decision Making
Probabilistic Inference

Education

Ph.D. in Electrical and Computer Engineering

2023 -- Present, Princeton University
B.E. in Computer Science and Technology

2017 -- 2021, Tsinghua University

Publications

A Survey on Transformers in Reinforcement Learning

TMLR Survey Certification

Wenzhe Li, Hao Luo, Zichuan Lin, Chongjie Zhang, Zongqing Lu, Deheng Ye

A Survey on Transformers in Reinforcement Learning

Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery

AAAI 2023 Oral Presentation

Yiqin Yang, Hao Hu, Wenzhe Li, Siyuan Li, Jun Yang, Qianchuan Zhao, Chongjie Zhang

Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery

Latent-Variable Advantage-Weighted Policy Optimization for Offline RL

NeurIPS 2022, L-DOD Workshop at RSS 2022

Xi Chen, Ali Ghadirzadeh, Tianhe Yu, Yuan Gao, Jianhao Wang, Wenzhe Li, Bin Liang, Chelsea Finn, Chongjie Zhang

Latent-Variable Advantage-Weighted Policy Optimization for Offline RL

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, Chongjie Zhang

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

Offline Reinforcement Learning with Reverse Model-based Imagination

Jianhao Wang, Wenzhe Li, Haozhe Jiang, Guangxiang Zhu, Siyuan Li, Chongjie Zhang

Offline Reinforcement Learning with Reverse Model-based Imagination

Estimating High Order Gradients of the Data Distribution by Denoising

Chenlin Meng, Yang Song, Wenzhe Li, Stefano Ermon

Estimating High Order Gradients of the Data Distribution by Denoising

Tractable Computation of Expected Kernels

Wenzhe Li, Zhe Zeng, Antonio Vergari, Guy Van den Broeck

Tractable Computation of Expected Kernels

Teaching

Deep Reinforcement Learning (TA)

Tsinghua University Mar 2022

Artificial Intelligence: Principles and Techniques (TA)

Tsinghua University Sep 2021

Contact

scott.wenzhe.li at gmail.com