Xiyao Wang (王玺尧)

Email: xywang@umd.edu
Google Scholar
Github

About me

I am a first year Ph.D. student in University of Maryland, College Park, where I am fortunate to be advised by Prof. Furong Huang. My research interest is reinforcement learning (RL), including model-based RL, transfer RL, exploration and exploitation, etc. My long-term goal is to make RL agents more efficient. Before that, I received my Bachelor’s degree in Network Engineering from University of Electronic Science and Technology of China (UESTC). I also worked as an research assistent in Institute of Automation, Chinese Academy of Sciences advised by Prof. Junge Zhang.

I am looking for internship opportunities. Here are my CV. Please feel free to contact me if you think I could be a good fit.

News and Highlights

    [2023.05]    1 paper accepted by ICML 2023! See you in Hawaii!
    [2023.01]    1 paper accepted by ICLR 2023!
    [2022.01]    1 paper accepted by ICLR 2022. Many thanks to my collaborators!
    [2021.03]    We won Runner-Up Award in NTIRE 2021 Challenge on Nonhomogeneous Dehazing and our paper got accepted by New Trends in Image Restoration and Enhancement Workshop in CVPR 2021! Many thanks to my Teammates!

Publications

Please see here for a full list of my publications.

ICML 2023          

Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy.

Xiyao Wang, Wichayaporn Wongkamjan, Ruonan Jia, and Furong Huang.
In the 40th International Conference on Machine Learning, 2023

Paper (Code coming soon!)

ICLR 2023          

Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function.

Ruijie Zheng*, Xiyao Wang*, Huazhe Xu, and Furong Huang. (* Equal Contribution)
In International Conference on Learning Representations, 2022

Paper (Code coming soon!)

ICLR 2022          

Transfer RL across Observation Feature Spaces via Model-Based Regularization.

Yanchao Sun, Ruijie Zheng, Xiyao Wang, Andrew Cohen, and Furong Huang.
In International Conference on Learning Representations, 2022

Paper     Code     HTML

CVPRW 2021          

A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning.

Yankun Yu, Huan Liu, Minghan Fu, Jun Chen, Xiyao Wang, Keyan Wang.
In New Trends in Image Restoration and Enhancement Workshop, CVPR 2021

Paper (Code coming soon!)

Please see here for a full list of my publications.