论文标题
学会在多代理隐藏角色游戏中欺骗
Learning to Deceive in Multi-Agent Hidden Role Games
论文作者
论文摘要
欺骗在人类社会环境中很普遍。但是，研究欺骗对增强学习算法的影响的研究仅限于简单化的设置，从而限制了它们对复杂的现实世界问题的适用性。本文通过引入一种新的混合竞争性合作的多代理增强学习（MARL）环境，灵感来自受欢迎的基于角色的欺骗游戏，例如狼人，阿瓦隆以及我们中间。环境的独特挑战在于，尽管不知道他们是朋友还是敌人，但必须与其他代理商合作。此外，我们引入了一种欺骗模型，我们称之为贝叶斯信仰操纵（BBM），并在这种环境下欺骗其他代理商，同时也提高了欺骗者的表现。
Deception is prevalent in human social settings. However, studies into the effect of deception on reinforcement learning algorithms have been limited to simplistic settings, restricting their applicability to complex real-world problems. This paper addresses this by introducing a new mixed competitive-cooperative multi-agent reinforcement learning (MARL) environment inspired by popular role-based deception games such as Werewolf, Avalon, and Among Us. The environment's unique challenge lies in the necessity to cooperate with other agents despite not knowing if they are friend or foe. Furthermore, we introduce a model of deception, which we call Bayesian belief manipulation (BBM) and demonstrate its effectiveness at deceiving other agents in this environment while also increasing the deceiving agent's performance.
