A Study of AI Agent Commitment in One Night Ultimate Werewolf with Human Players
A Study of AI Agent Commitment in One Night Ultimate Werewolf with Human Players
复制标题
《一夜终极狼人杀》中人工智能代理与人类玩家的承诺研究
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Chris Martens
中科院分区：
文献类型：
--
作者：
Markus Eger;Chris Martens
社会推理游戏是一种棋盘游戏，其中一组玩家被秘密分配角色，每个玩家试图确定其他玩家的角色。然而，有些角色有不被发现的动机，游戏通常允许玩家自由撒谎。玩这样的游戏对AI代理来说是一项具有挑战性的任务，因为他们不仅需要确定其他玩家所做的每个陈述是真实的概率，而且还需要自己提出令人信服的谎言。在本文中，我们提出了人工智能代理，旨在发挥一个特定的这样的游戏，一夜终极狼人，与人类玩家。我们讨论了我们的代理使用不同的审议策略，以确定他们应该说什么，以及何时他们应该改变他们的计划。为了确定这些不同的审议策略是如何被人类玩家感知的，我们进行了一个实验，在这个实验中，参与者使用三种审议策略中的每一种来玩游戏的Unity实现。我们提出了这个实验的结果，这表明，承诺计划有一个可衡量的影响球员的看法，并提供了一致性和高性能的代理潜力之间的权衡。
Social deduction games are a genre of board games in which a group of players is secretly assigned roles and each player tries to determine the other players’ roles. However, some roles have an incentive to not be found, and the games typically allow players to lie freely. Playing such games is a challenging task for AI agents, because they need to not only determine the probability that each statement made by the other players is truthful, but also come up with convincing lies themselves. In this paper, we present AI agents designed to play one particular such game, One Night Ultimate Werewolf, with human players. We discuss the different deliberation strategies our agents use to determine what they should say, and when they should change their plan. To determine how these different deliberation strategies are perceived by human players, we performed an experiment in which participants played a Unity implementation of the game with each of the three deliberation strategies. We present the results of this experiment, which show that commitment to plans has a measurable effect on player perception and provide a trade-off between consistency and potential for high performance of the agent.