Youzhi Zhang

Associate Professor@Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences·中国香港·OpenReview

研究方向

AI for Drug Discovery · Multi-agent optimization · Reinforcement Learning · Online learning · Computational game theory and its application to security · Optimization

Youzhi Zhang

A Faster Parameter-Free Regret Matching Algorithm

Offline Equilibrium Finding in Extensive-form Games: Datasets, Methods, and Analysis

Reducing Variance of Stochastic Optimization for Approximating Nash Equilibria in Normal-Form Games

Efficient Last-Iterate Convergence in Solving Extensive-Form Games

Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

POC: Preventing the Over-Collapse of Classes for Class-Incremental Learning

Solving Urban Network Security Games: Learning Platform, Benchmark, and Challenge for AI Research

In-Context Learning for Games

Direct Alignment of Language Models via Quality-Aware Self-Refinement

Offline Equilibrium Finding in Extensive-form Games: Datasets, Methods, and Analysis

Computing Ex Ante Equilibrium in Heterogeneous Zero-Sum Team Games

Learning Nash Equilibria in Normal-Form Games via Approximating Stationary Points