Alert button
Picture for Xiaojin Zhu

Xiaojin Zhu

Alert button

Optimal Attack and Defense for Reinforcement Learning

Add code
Bookmark button
Alert button
Nov 30, 2023
Jeremy McMahan, Young Wu, Xiaojin Zhu, Qiaomin Xie

Viaarxiv icon

Optimally Teaching a Linear Behavior Cloning Agent

Add code
Bookmark button
Alert button
Nov 26, 2023
Shubham Kumar Bharti, Stephen Wright, Adish Singla, Xiaojin Zhu

Viaarxiv icon

Learning interactions to boost human creativity with bandits and GPT-4

Add code
Bookmark button
Alert button
Nov 16, 2023
Ara Vartanian, Xiaoxi Sun, Yun-Shiuan Chuang, Siddharth Suresh, Xiaojin Zhu, Timothy T. Rogers

Figure 1 for Learning interactions to boost human creativity with bandits and GPT-4
Figure 2 for Learning interactions to boost human creativity with bandits and GPT-4
Figure 3 for Learning interactions to boost human creativity with bandits and GPT-4
Figure 4 for Learning interactions to boost human creativity with bandits and GPT-4
Viaarxiv icon

Anytime-Constrained Reinforcement Learning

Add code
Bookmark button
Alert button
Nov 14, 2023
Jeremy McMahan, Xiaojin Zhu

Viaarxiv icon

Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value

Add code
Bookmark button
Alert button
Nov 02, 2023
Young Wu, Jeremy McMahan, Yiding Chen, Yudong Chen, Xiaojin Zhu, Qiaomin Xie

Viaarxiv icon

Dream the Impossible: Outlier Imagination with Diffusion Models

Add code
Bookmark button
Alert button
Sep 23, 2023
Xuefeng Du, Yiyou Sun, Xiaojin Zhu, Yixuan Li

Figure 1 for Dream the Impossible: Outlier Imagination with Diffusion Models
Figure 2 for Dream the Impossible: Outlier Imagination with Diffusion Models
Figure 3 for Dream the Impossible: Outlier Imagination with Diffusion Models
Figure 4 for Dream the Impossible: Outlier Imagination with Diffusion Models
Viaarxiv icon

VISER: A Tractable Solution Concept for Games with Information Asymmetry

Add code
Bookmark button
Alert button
Jul 18, 2023
Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu, Qiaomin Xie

Figure 1 for VISER: A Tractable Solution Concept for Games with Information Asymmetry
Figure 2 for VISER: A Tractable Solution Concept for Games with Information Asymmetry
Figure 3 for VISER: A Tractable Solution Concept for Games with Information Asymmetry
Figure 4 for VISER: A Tractable Solution Concept for Games with Information Asymmetry
Viaarxiv icon

On Faking a Nash Equilibrium

Add code
Bookmark button
Alert button
Jun 13, 2023
Young Wu, Jeremy McMahan, Xiaojin Zhu, Qiaomin Xie

Figure 1 for On Faking a Nash Equilibrium
Figure 2 for On Faking a Nash Equilibrium
Viaarxiv icon

Non-Parametric Outlier Synthesis

Add code
Bookmark button
Alert button
Mar 06, 2023
Leitian Tao, Xuefeng Du, Xiaojin Zhu, Yixuan Li

Figure 1 for Non-Parametric Outlier Synthesis
Figure 2 for Non-Parametric Outlier Synthesis
Figure 3 for Non-Parametric Outlier Synthesis
Figure 4 for Non-Parametric Outlier Synthesis
Viaarxiv icon

Provable Defense against Backdoor Policies in Reinforcement Learning

Add code
Bookmark button
Alert button
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
Viaarxiv icon