Hi, I am Qi Zhang, an assistant professor at WPI. I work on building collaborative AI agents. My research interests are in formalisms, theories, and algorithms of single- and multi-agent planning and reinforcement learning.

2025 - Now    Assistant Professor, CS/AI @ WPI
2020 - 2025   Assistant Professor, CSE/AI @ U of South Carolina
2015 - 2020   PhD, CSE @ U of Michigan

Email: qzhang9 at wpi.edu      Office: Unity Hall 355

I am looking for PhD students and visiting researchers!

Selected Papers

Google Scholar

• Natural Policy Gradient for Bayesian Network Policies in Markov Potential Games
  Dingyang Chen, Zhenyu Zhang, Yuan Ling, Qi Zhang
  RL Conference 2026  

• Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
  Jiancheng Zhang, Meiqing Li, Qi Zhang, Yinglun Zhu
  ICML 2026  

• Analyzing Best-Response Dynamics for Cooperation in Markov Potential Games
  Dingyang Chen, Xiaoling Zeng, Thinh T. Doan, Qi Zhang
  TMLR (2026)  

• Tree of Options: Temporally Extended World Modeling, Planning, and Execution with Large Language Models
  Xiaoling Zeng, Dingyang Chen, Qi Zhang
  ICLR 2026 Workshop on World Models   [openreview]

• Correlated Policy Optimization in Multi-Agent Subteams
  Dingyang Chen, Jianing Ye, Zhenyu Zhang, Xiaolong Kuang, Xinyang Shen, Ozalp Ozer, Chongjie Zhang, Qi Zhang
  ICLR 2026   [openreview]

• Efficient Information Sharing for Training Decentralized Multi-Agent World Models
  Xiaoling Zeng, Qi Zhang
  RL Conference 2025   [openreview]

• Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
  Jinzhu Luo, Dingyang Chen, Qi Zhang
  NeurIPS 2024   [arXiv]

• Efficient Sequential Decision Making with Large Language Models
  Dingyang Chen, Qi Zhang, Yinglun Zhu
  EMNLP 2024   [arXiv]

• E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  Dingyang Chen, Qi Zhang
  ICML 2024   [arXiv]

• Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  Dingyang Chen, Qi Zhang
  ICML 2023   [openreview]

• Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
  Dingyang Chen, Qi Zhang, Thinh T. Doan
  ICML 2022 DARL Workshop   [arXiv]

• Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games
  Dingyang Chen, Yile Li, Qi Zhang
  ICLR 2022   [openreview]