学会策略性讨论:以《一夜终极狼人》为例的研究
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
AI总结:
该研究针对大语言模型智能体缺乏讨论策略把控的问题,以《一夜终极狼人》为对象证明讨论对博弈收益的重要性,提出强化学习引导的语言智能体框架,验证了其有效性与泛化性。
摘要:
沟通是人类社会的基本要素,促进了人与人之间的信息与信念交换。尽管大语言模型(LLMs)已取得进展,但近期基于这些模型构建的智能体往往忽视对讨论策略的把控,而这类策略在沟通场景和博弈中至关重要。作为知名沟通博弈《狼人》的变体,《一夜终极狼人》(One Night Ultimate Werewolf,ONUW)因存在可能的身份转换提升了博弈的不确定性与复杂度,要求玩家制定策略性的讨论策略。本研究首先证明了完美贝叶斯均衡(Perfect Bayesian Equilibria,PBEs)在ONUW博弈的两种场景下的存在性:含讨论的场景与不含讨论的场景。结果表明,讨论通过影响玩家的信念极大地改变了玩家的收益,凸显了讨论策略的重要性。基于分析得出的洞见,我们提出了一种由强化学习(RL)引导的语言智能体框架,该框架采用经强化学习训练的讨论策略来确定应采用的合适讨论战术。我们在多种ONUW博弈设置下的实验结果证明了所提框架的有效性与泛化性。本文的项目页面为:$\href{https://one-night-ultimate-werewolf.github.io}{one-night-ultimate-werewolf.github.io}$。
英文摘要:
Communication is a fundamental aspect of human society, facilitating the exchange of information and beliefs among people. Despite the advancements in large language models (LLMs), recent agents built with these often neglect the control over discussion tactics, which are essential in communication scenarios and games. As a variant of the famous communication game Werewolf, One Night Ultimate Werewolf (ONUW) requires players to develop strategic discussion policies due to the potential role changes that increase the uncertainty and complexity of the game. In this work, we first present the existence of the Perfect Bayesian Equilibria (PBEs) in two scenarios of the ONUW game: one with discussion and one without. The results showcase that the discussion greatly changes players' utilities by affecting their beliefs, emphasizing the significance of discussion tactics. Based on the insights obtained from the analyses, we propose an RL-instructed language agent framework, where a discussion policy trained by reinforcement learning (RL) is employed to determine appropriate discussion tactics to adopt. Our experimental results on several ONUW game settings demonstrate the effectiveness and generalizability of our proposed framework. The project page of our paper: $\href{https://one-night-ultimate-werewolf.github.io}{one-night-ultimate-werewolf.github.io}$.
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。