1

Is Nash Equilibrium Approximator Learnable?

In this paper, we investigate the learnability of the function approximator that approximates Nash equilibrium (NE) for games generated …

Zhijian Duan, Wenhan Huang, Dinghuai Zhang, Yali Du, Jun Wang, Yaodong Yang, Xiaotie Deng

GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning …

Hanjing Wang, Man-Kit Sit, Congjie He, Ying Wen, Weinan ZHANG, Jun Wang, Yaodong Yang, Luo MAI

A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems

In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other …

Oliver Slumbers, David Henry Mguni, Stephen Marcus McAleer, Stefano B. Blumberg, Jun Wang, Yaodong Yang

Regret-Minimizing Double Oracle for Extensive-Form Games

By incorporating regret minimization, double oracle methods have demonstrated rapid convergence to Nash Equilibrium (NE) in normal-form …

Xiaohang Tang, Le Cong Dinh, Stephen Marcus McAleer, Yaodong Yang

MANSA: Learning Fast and Slow in Multi-Agent Systems

In multi-agent reinforcement learning (MARL), independent learning (IL) often shows remarkable performance and easily scales with the …

David Mguni, Haojun Chen, Taher Jafferjee, Jianhong Wang, Long Fei, Xidong Feng, Stephen McAleer, Feifei Tong, Jun Wang, Yaodong Yang

Learning to Shape Rewards using a Game of Two Partners

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. …

David Mguni, Taher Jafferjee, Jianhong Wang, Nicolas Perez-Nieves, Tianpei Yang, Matthew Taylor, Wenbin Song, Feifei Tong, Hui Chen, Jiangcheng Zhu, Jun Wang, Yaodong Yang

Quality-Similar Diversity via Population Based Reinforcement Learning

Diversity is a growing research topic in Reinforcement Learning (RL). Previous research on diversity has mainly focused on promoting …

Shuang Wu, Jian Yao, Haobo Fu, Ye Tian, Chao Qian, Yaodong Yang, QIANG FU, Yang Wei

A game-theoretic approach to multi-agent trust region optimization

Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement …

Ying Wen, Hui Chen, Yaodong Yang, Minne Li, Zheng Tian, Xu Chen, Jun Wang

ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency

Multi-agent reinforcement learning (MARL) suffers from the non-stationarity problem, which is the ever-changing targets at every …

Chuming Li, Jie Liu, Yinmin Zhang, Yuhong Wei, Yazhe Niu, Yaodong Yang, Yu Liu, Wanli Ouyang

Contextual Transformer for Offline Meta Reinforcement Learning

The pretrain-finetuning paradigm in large-scale sequence models has made significant progress in natural language processing and …

Runji LIN, Ye Li, Xidong Feng, Zhaowei Zhang, Xian Hong Wu Fung, Haifeng ZHANG, Jun Wang, Yali Du, Yaodong Yang