Large Language Model-enhanced Reinforcement Learning for Low-Altitude Economy Networking
This work addresses networking problems for aerial applications below 1,000 meters, but it is incremental as it combines existing LLM and RL methods.
The paper tackles the challenges of Low-Altitude Economic Networking (LAENet), such as complex decision-making and resource constraints, by proposing an LLM-enhanced RL framework, and demonstrates improved learning performance through a case study using LLMs for reward design.
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.