Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
CoRR(2023)
摘要
Agents built with large language models (LLMs) have shown great potential
across a wide range of domains. However, in complex decision-making tasks, pure
LLM-based agents tend to exhibit intrinsic bias in their choice of actions,
which is inherited from the model's training data and results in suboptimal
performance. To develop strategic language agents, i.e., agents that generate
flexible language actions and possess strong decision-making abilities, we
propose a novel framework that powers LLM-based agents with reinforcement
learning (RL). We consider Werewolf, a popular social deduction game, as a
challenging testbed that emphasizes versatile communication and strategic
gameplay. To mitigate the intrinsic bias in language actions, our agents use an
LLM to perform deductive reasoning and generate a diverse set of action
candidates. Then an RL policy trained to optimize the decision-making ability
chooses an action from the candidates to play in the game. Extensive
experiments show that our agents overcome the intrinsic bias and outperform
existing LLM-based agents in the Werewolf game. We also conduct human-agent
experiments and find that our agents achieve human-level performance and
demonstrate strong strategic play.
更多查看译文
关键词
reinforcement learning,agents,language,strategic play
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要