Publications

Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL

The Tenth International Conference on Learning Representations (ICLR), 2022.
Yanchao Sun, Ruijie Zheng, Yongyuan Liang, Furong Huang
Publisher's website BibTeX

Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory

The Tenth International Conference on Learning Representations (ICLR), 2022.
Zhi Zhang, Zhuoran Yang, Han Liu, Pratap Tokekar, Furong Huang
Publisher's website BibTeX

Transfer RL across Observation Feature Spaces via Model-Based Regularization

The Tenth International Conference on Learning Representations (ICLR), 2022.
Yanchao Sun, Ruijie Zheng, Xiyao Wang, Andrew E Cohen, Furong Huang
Publisher's website BibTeX

Understanding the Generalization Benefit of Model Invariance from a Data Perspective

Neural Information Processing System (NeurIPS), 2021.
Sicheng Zhu, Bang An, Furong Huang
Publisher's website BibTeX

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

Neural Information Processing System (NeurIPS), 2021.
Mucong Ding, Kezhi Kong, Jingling Li, Chen Zhu, John P Dickerson, Furong Huang, Tom Goldstein
BibTeX

Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks

Neural Information Processing System (NeurIPS), 2021.
Avi Schwarzschild, Eitan Borgnia, Arjun Gupta, Furong Huang, Uzi Vishkin, Micah Goldblum, Tom Goldstein
Publisher's website BibTeX

Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics

9th International Conference on Learning Representations (ICLR), 2021.
Yanchao Sun, Da Huo, Furong Huang
Publisher's website BibTeX

TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL

35th AAAI Conference on Artificial Intelligence, 2021.
Yanchao Sun, Xiangyu Yin, Furong Huang
Publisher's website BibTeX

Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-Uniform Attacks

35th AAAI Conference on Artificial Intelligence (AAAI), 2021.
Huimin Zeng, Chen Zhu, Tom Goldstein and Furong Huang
Publisher's website BibTeX

Certifiably Robust Multi-Agent Reinforcement Learning against Adversarial Communication

accepted to the Responsible Decision Making in Dynamic Environments Workshop @ICML2022.
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang, Soheil Feizi, Sumitra Ganesh, Furong Huang
BibTeX