Picture for Xuezhou Zhang

Xuezhou Zhang

Provable Defense against Backdoor Policies in Reinforcement Learning

Nov 18, 2022
Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla, Xiaojin Zhu

Figure 1 for Provable Defense against Backdoor Policies in Reinforcement Learning

Figure 2 for Provable Defense against Backdoor Policies in Reinforcement Learning

Figure 3 for Provable Defense against Backdoor Policies in Reinforcement Learning

Figure 4 for Provable Defense against Backdoor Policies in Reinforcement Learning

* Accepted at Neurips 2022

Access Paper or Ask Questions

Byzantine-Robust Online and Offline Distributed Reinforcement Learning

Jun 01, 2022
Yiding Chen, Xuezhou Zhang, Kaiqing Zhang, Mengdi Wang, Xiaojin Zhu

Access Paper or Ask Questions

Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory

Feb 10, 2022
Ruiqi Zhang, Xuezhou Zhang, Chengzhuo Ni, Mengdi Wang

Figure 1 for Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory

* 39 pages

Access Paper or Ask Questions