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 2307.15833cs.CL
收藏

Dialogue Shaping:通过NPC交互赋能智能体

Dialogue Shaping: Empowering Agents through NPC Interaction

Georgia Institute of Technology(佐治亚理工学院)

Wei Zhou, Xiangyu Peng, Mark Riedl

AI总结:

本文针对文本游戏中强化学习智能体训练收敛慢的问题,提出利用大型语言模型与NPC交互获取关键信息,并结合知识图谱和Story Shaping技术加速智能体训练。

摘要:

强化学习(RL)的一大挑战是,RL智能体在训练过程中需要大量步骤才能收敛并学习到最优策略,尤其是在动作空间庞大的基于文本的游戏环境中。然而,非玩家角色(NPCs)有时掌握着关于游戏的一些关键信息,这些信息有可能帮助更快地训练RL智能体。因此,本文探索了如何利用大型语言模型(LLMs)与NPC智能体进行交互和对话以获取关键信息,并利用知识图谱(KGs)和Story Shaping整合这些信息,从而加速RL智能体的训练。

英文摘要:

One major challenge in reinforcement learning (RL) is the large amount of steps for the RL agent needs to converge in the training process and learn the optimal policy, especially in text-based game environments where the action space is extensive. However, non-player characters (NPCs) sometimes hold some key information about the game, which can potentially help to train RL agents faster. Thus, this paper explores how to interact and converse with NPC agents to get the key information using large language models (LLMs), as well as incorporate this information to speed up RL agent's training using knowledge graphs (KGs) and Story Shaping.

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。

↑