I am currently a tenure-track Assistant Professor in the Department of Computer Science and Engineering at the University of South Carolina, USA.
Before the current appointment that started from August 2020, I obtained my PhD degree in 2020 from the Computer Science and Engineering division at the University of Michigan, Ann Arbor, and my BEng degree in 2015 from the Department of Electronic Engineering at Shanghai Jiao Tong University.
My research interests lie in artificial intelligence, with a special focus on cooperative artificial intelligence, which equips a group of sequential decision makers, or autonomous agents, with the capability of maximizing their joint utility.
My long-term career goal is to improve the efficiency of solutions to cooperative AI by exploiting structural properties inherent in these problems.
To achieve this goal, I have been developing expertise in the formalisms, theories, and algorithms of single- and multi-agent planning and reinforcement learning, as well as their applications to domains such as intelligent transportation systems, computational materials science, and clinical natural language processing.
News
2024/9: One paper accepted to NeurIPS 2024.
2024/9: One paper accepted to EMNLP 2024.
2024/8: Awarded
an NSF grant from its Robust Intelligence (RI) on Foundation Models + Sequential Decision Making.
2024/5: One paper accepted to ICML 2024.
2023/9: Two papers accepted to CoRL 2023 workshops.
2023/9: One paper accepted to the MAD-Games Workshop at IROS 2023.
2023/4: One paper accepted to ICML 2023.
2023/3: One paper accepted to Artificial Intelligence (AIJ).
2023/2: I received an
NSF CAREER Award from IIS.
2022/12: We are organizing
the 8th Deep Reinforcement Learning Workshop at NeurIPS 2022.
2022/11: Awarded an
exploreCSR grant from Google Research. Check out
our exploreCSR program.
2022/7: Awarded
an NSF grant from CISE Community Research Infrastructure (CCRI).
2022/6: Awarded
an NSF grant from IIS: Robust Intelligence (RI).
2022/6: One paper accepted to workshops at ICML 2022.
2022/4: One paper accepted to IJCNN 2022.
2022/1: One paper accepted to ICLR 2022.
2021/10: Two papers accepted to NeurIPS 2021 workshops.
2021/6: One paper accepted to ECML PKDD 2021.
2021/5: Presenting at ALA workshop at AAMAS 2021.
2021/4: Awarded an ASPIRE I grant from the Office of Research at the University of South Carolina.
2021/3: Presenting at COMARL AAAI 2021 Spring Symposium.
2021/3: Selected to be the inaugural recipient of the David J. Kuck CSE Dissertation Prize.
2020/12: One paper accepted to AAAI 2021.
2020/4: Defended my PhD dissertation.
Papers
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
[
arXiv]
(NeurIPS 2024)
Jinzhu Luo, Dingyang Chen, Qi Zhang
Efficient Sequential Decision Making with Large Language Models
[
arXiv]
(EMNLP 2024)
Dingyang Chen, Qi Zhang, Yinglun Zhu
E(3)-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
[
arXiv]
(ICML 2024)
Dingyang Chen, Qi Zhang
Subgoal Proposition Using a Vision-Language Model
[
link]
(Workshop on Language and Robot Learning (LangRob) at IROS 2023)
Jianhai Su, Qi Zhang
Exploiting MDP Symmetries for Offline Reinforcement Learning
[
link]
(Workshop on Learning Effective Abstractions for Planning (LEAP) at IROS 2023)
Jinzhu Luo, Qi Zhang
Intent-Aware Autonomous Driving: A Case Study on Highway Merging Scenarios
[
arXiv]
(MAD-Games Workshop at IROS 2023)
Nishtha Mahajan, Qi Zhang
Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
[
arXiv,
link]
(ICML 2023)
Dingyang Chen, Qi Zhang
Risk-Aware Analysis for Interpretations of Probabilistic Achievement and Maintenance Commitments
[
link]
(AIJ, 2023)
Qi Zhang, Edmund Durfee, Satinder Singh
Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games
[
arXiv]
(Preprint)
Dingyang Chen, Qi Zhang, Thinh T. Doan
(Presented at workshops at ICML 2022)
Ensemble Policy Distillation with Reduced Data Distribution Mismatch
[
link]
(IJCNN 2022)
Yuxiang Sun, Qi Zhang
Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games
[
link]
(ICLR 2022)
Dingyang Chen, Yile Li, Qi Zhang
(Also presented at Deep RL Workshop at NeurIPS 2021
[
workshop version]
)
A Meta-Gradient Approach to Learning Cooperative Multi-Agent Communication Topology
[
link]
(Workshop on Meta-Learning at NeurIPS 2021)
Qi Zhang, Dingyang Chen
Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits
[
link]
(ECML PKDD 2021)
Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth
(Also presented at the ALA workshop at AAMAS 2021
[
workshop version]
)
Knowledge Infused Policy Gradients for Adaptive Pandemic Control
[
arXiv]
(AAAI-MAKE 2021)
Kaushik Roy, Qi Zhang, Manas Gaur, Amit Sheth
Efficient Querying for Cooperative Probabilistic Commitments
[
arXiv]
(AAAI 2021)
Qi Zhang, Edmund Durfee, Satinder Singh
Semantics and Algorithms for Trustworthy Commitment Achievement under Model Uncertainty
[
link]
(JAAMAS, 2020)
Qi Zhang, Edmund Durfee, Satinder Singh
Modeling Probabilistic Commitments for Maintenance Is Inherently Harder than for Achievement
[
pdf]
(AAAI 2020)
Qi Zhang, Edmund Durfee, Satinder Singh
Learning to Communicate and Solve Visual Blocks-World Tasks
[
pdf]
(AAAI 2019)
Qi Zhang, Richard Lewis, Satinder Singh, Edmund Durfee
Challenges in the Trustworthy Pursuit of Maintenance Commitments under Uncertainty
[
pdf]
(Trust Workshop at AAMAS 2018)
Qi Zhang, Edmund Durfee, Satinder Singh
Minimizing Maximum Regret in Commitment Constrained Sequential Decision Making
[
pdf,
arXiv]
(ICAPS 2017)
Qi Zhang, Satinder Singh, Edmund Durfee
Commitment Semantics for Sequential Decision Making Under Reward Uncertainty
[
pdf]
(IJCAI 2016)
Qi Zhang, Edmund Durfee, Satinder Singh, Anna Chen, Stefan Witwicki
Incentivize Crowd Labeling under Budget Constraint
[
link]
(INFOCOM-15)
Qi Zhang, Yutian Wen, Xiaohua Tian, Xiaoying Gan, Xinbing Wang
Quality-Driven Auction based Incentive Mechanism for Mobile Crowd Sensing
[
link]
(IEEE TVT, 2015)
Yutian Wen, Jinyu Shi, Qi Zhang, Xiaohua Tian, Zhengyong Huang, Hui Yu, Yu Cheng, Xuemin (Sherman) Shen