Assistant Professor
Department of Electrical and Computer Engineering, University of Central Florida
Office: HEC-442
Email: yue.wang@ucf.edu, ywang294@buffalo.edu
Google Scholar: Yue Wang's Google Scholar
About me.
I am an Assistant Professor at the Department of Electrical and Computer Engineering (joint appointment with the Computer Science Department), University of Central Florida. I am also affiliated with the Artificial Intelligence Initiative.
I received my Ph.D. degree in Electrical engineering from The State University of New York at Buffalo in 2023, under the advisory of Prof. Shaofeng Zou, and my B.S. degree in mathematics from Nanjing University in 2019.
Research Interests.
My research interests specialize in machine learning, with a primary focus on reinforcement learning (RL), optimization, and generative models. Below are some of the topics I am exploring or want to explore:
Algorithm design and analysis in reinforcement learning
Transfer learning in RL
Robust RL and reliable decision making system
Generative models in RL
LLM in RL
Prospective Students.
I am seeking highly motivated Ph.D. students with backgrounds in math, statistics, computer science, or electrical engineering. If you are interested in working with me, please send an email with your CV and transcripts.
Undergraduate and graduate students at UCF are highly encouraged to contact me for research opportunities if you are interested in my work.
Students whom I have never met before, DO NOT cold email me about getting you a grader/TA job. Please ping the department.
News
Paper: Our paper "A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch" has been accepted by NeurIPS 2024.
Paper: Our paper "Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward" has been accepted by IEEE TIT.
Paper: Our paper "Achieving the Asymptotically Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach" has been accepted by TMLR.
Paper: Our paper "Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation" has been accepted by ICML 2024.
Paper: Our paper "Model-Free Robust Reinforcement Learning with Sample Complexity Analysis" has been accepted by UAI 2024.
Paper: Our paper "Finite-time error bounds for Greedy-GQ" has been accepted by Machine Learning.
Grant: Our "Distributionally Robust Approaches to Transfer Learning" (Co-PI) project has been awarded a prestigious DARPA Award totaling $1.23M, part of DARPA's Transfer from Imprecise and Abstract Models to Autonomous Technologies Program. Thanks, DARPA!
Paper: Our paper "Robust average-reward reinforcement learning" has been accepted by the Journal of Artificial Intelligence Research (JAIR).