898_shangtong20photo-1--converted-from-webp.png

Shangtong Zhang

Reinforcement Learning Theoretical Reinforcement Learning Empirical Reinforcement Learning Sequential Decision Making
University of Virginia Department of Computer Science

About

Shangtong Zhang is an Alf Weaver Assistant Professor in the Department of Computer Science at the University of Virginia, directing the Sequential Intelligence Lab (SIL). His research focuses on both theoretical and empirical aspects of reinforcement learning, resulting in multiple scholarly articles in major AI venues, e.g., JMLR, NeurIPS, ICML, and ICLR. He also regularly serves as Area Chair in major AI venues, e.g., NeurIPS, ICML, ICLR, Senior Area Chair in RL Conference, and panelists for major federal funding agencies, e.g., NSF. He and his research are recognized by multiple awards and honors, including best paper awards at ICML workshop and AAMAS, NSF CAREER Award, AAAI New Faculty Highlights, Rising Star in AI, and IFAAMAS Victor Lesser Dissertation Award. He obtained his DPhil at the University of Oxford, MSc at the University of Alberta, and BSc at Fudan University.

Research Performance Summary

53
Total Papers
1818
Total Citations
20
H-Index
2015-2026
Active Research Span

First Recorded Paper

A deep neural network for modeling music

Year: 2015

Citations: 31

Venue: Proceedings of the 5th ACM on International Conference on Multimedia

Latest Recorded Paper

Multi-agent DRL-based Lane Change Decision Model for Cooperative Planning in Mixed Traffic

Year: 2026

Citations: 0

Venue: arXiv preprint arXiv:2601.11809

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

2026
1
2025
16
2024
8
2023
3
2022
2
2021
5
2020
3
2019
6
2018
5
2017
3
2015
1

Publication Venues and Collaboration

Journal, Conference, and Book Publication Breakdown

Conference 9
Journal 4
Book 2

Top Coauthors

Zhang Liu Whiteson

Research Impact by Period

2025-2026

Period Stats
Papers 17
Citations 87
Avg. Citations / Paper 5.1
H-Index 6

2020-2024

Period Stats
Papers 21
Citations 569
Avg. Citations / Paper 27.1
H-Index 12

2015-2019

Period Stats
Papers 15
Citations 1162
Avg. Citations / Paper 77.5
H-Index 13

Contact and Professional Links

Contact Information

shangtong@virginia.edu

Detected Research Keywords

Off Policy Actor Policy Actor Critic Context Reinforcement Learning Finite Sample Analysis Efficient Policy Evaluation Temporal Difference Learning Breaking Deadly Triad Temporal Difference Methods Stochastic Approximation Reinforcement Approximation Reinforcement Learning