Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods
It provides a framework for researchers to systematically apply LLMs in RL, potentially accelerating applications in domains like robotics and autonomous driving, but it is incremental as it synthesizes existing literature without new empirical results.
This survey reviews how large language models (LLMs) can enhance reinforcement learning (RL) by addressing challenges like multi-task learning and sample efficiency, proposing a taxonomy that categorizes LLMs into four roles to guide future research.
With extensive pre-trained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects such as multi-task learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared to conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs' functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated, and provide insights into future directions. Lastly, a comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications such as robotics, autonomous driving, and energy systems.