LLM4RL: Enhancing Reinforcement Learning with Large Language Models
Jiehan Zhou, Yang Zhao, Jiahong Liu, Peijun Dong, Xiaoyu Luo, Hang Tao, Shi‐Chung Chang, Hanjiang Luo · 2024
Integrating large language models (LLMs) into reinforcement learning (RL) promises to enhance the learning performance. Traditional RL faces challenges in industrial settings, including complex environments, safety concerns, and multimodal data. As powerful tools for contextual learning and reasoning, LLMs can address issues inherent in traditional RL. This paper introduces a generic LLM4RL framework, and investigates how LLM4RL can improve learning performance in autonomous driving.