arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.05575cs.AIcs.GT
收藏

用于扩展式博弈的上下文内利用者(In-Context Exploiter)

In-Context Exploiter for Extensive-Form Games

Nanyang Technological University(南洋理工大学);The Hong Kong Polytechnic University(香港理工大学);CAIR, HKISI, CAS(中国科学院香港中文大学信息工程研究所(注:CAIR为Computational Intelligence and Robotics,HKISI为Hong Kong Institute of Science Innovation,CAS为Chinese Academy of Sciences));Singapore Management University(新加坡管理大学);University of Nebraska(内布拉斯加大学)

Shuxin Li, Chang Yang, Youzhi Zhang, Pengdeng Li, Xinrun Wang, Xiao Huang, Hau Chan, Bo An

AI总结:

针对纳什均衡策略对抗非均衡对手时效果不佳的问题,提出基于上下文学习的ICE方法,通过多样对手策略生成、强化学习采数与课程学习训练transformer智能体,可自适应利用任意未知对手最大化自身效用。

摘要:

纳什均衡(Nash equilibrium, NE)是博弈论中因具备稳定性而被广泛采用的解概念。然而我们观察到,NE策略未必总能带来最优结果,尤其是在对抗不遵循NE策略的对手时。基于这一观察,我们提出一个全新的博弈求解问题:我们能否学习一个模型,它可以利用任意对手(甚至是采用NE策略的对手)来最大化自身效用?在本研究中,我们首次尝试通过上下文学习(in-context learning)探究该问题。具体而言,我们提出了一种新方法——上下文内利用者(In-Context Exploiter, ICE),用于训练单个模型,使其能够在博弈中扮演任意玩家角色,并完全通过上下文学习自适应地利用对手。我们的ICE算法包含生成多样化的对手策略、通过强化学习算法收集交互历史训练数据,以及在精心设计的课程学习框架内训练基于transformer的智能体。最后,综合实验结果验证了ICE算法的有效性,展现了其利用任意未知对手的上下文学习能力,从而对我们最初提出的博弈求解问题给出了肯定回答。

英文摘要:

Nash equilibrium (NE) is a widely adopted solution concept in game theory due to its stability property. However, we observe that the NE strategy might not always yield the best results, especially against opponents who do not adhere to NE strategies. Based on this observation, we pose a new game-solving question: Can we learn a model that can exploit any, even NE, opponent to maximize their own utility? In this work, we make the first attempt to investigate this problem through in-context learning. Specifically, we introduce a novel method, In-Context Exploiter (ICE), to train a single model that can act as any player in the game and adaptively exploit opponents entirely by in-context learning. Our ICE algorithm involves generating diverse opponent strategies, collecting interactive history training data by a reinforcement learning algorithm, and training a transformer-based agent within a well-designed curriculum learning framework. Finally, comprehensive experimental results validate the effectiveness of our ICE algorithm, showcasing its in-context learning ability to exploit any unknown opponent, thereby positively answering our initial game-solving question.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑