Prompt-to-policy: Leveraging large language models to guide deep reinforcement learning in public health emergencies

Executive Summary

The article discusses a hybrid agent that integrates D2QN-JDA with large language models (LLMs) for dynamic decision-making in public health emergencies. LLMs with retrieval-augmented generation (RAG) process multi-source heterogeneous data to calculate adaptive rewards. The agent is validated with pandemic data from Hong Kong, outperforming baselines in cost efficiency and robustness. The study highlights the use of LLMs to automate the processing of heterogeneous, real-time data, reducing manual intervention and enhancing system robustness. The proposed method demonstrates superior performance in accuracy, recall, F1 score, cost, and time compared to traditional methods.