Large Language Model-enhanced Reinforcement Learning for Low-Altitude Economy Networking

TL;DR

This paper explores integrating large language models into reinforcement learning to enhance decision-making and reward design for low-altitude aerial networking, addressing environmental and resource challenges.

Contribution

It introduces a novel LLM-enhanced RL framework for LAENet, leveraging LLMs for information processing, reward design, and decision-making, with a case study on reward function optimization.

Findings

LLMs can effectively serve as information processors in RL for LAENet.

Using LLMs to design reward functions improves RL performance.

The framework demonstrates potential for flexible aerial network management.

Abstract

Low-Altitude Economic Networking (LAENet) aims to support diverse flying applications below 1,000 meters by deploying various aerial vehicles for flexible and cost-effective aerial networking. However, complex decision-making, resource constraints, and environmental uncertainty pose significant challenges to the development of the LAENet. Reinforcement learning (RL) offers a potential solution in response to these challenges but has limitations in generalization, reward design, and model stability. The emergence of large language models (LLMs) offers new opportunities for RL to mitigate these limitations. In this paper, we first present a tutorial about integrating LLMs into RL by using the capacities of generation, contextual understanding, and structured reasoning of LLMs. We then propose an LLM-enhanced RL framework for the LAENet in terms of serving the LLM as information processor, reward designer, decision-maker, and generator. Moreover, we conduct a case study by using LLMs to design a reward function to improve the learning performance of RL in the LAENet. Finally, we provide a conclusion and discuss future work.