A general framework for optimising cost-effectiveness of pandemic response under partial intervention measures

This project is a classic academic reference implementation accompanying an arXiv paper. With 0 stars and no activity in nearly four years, it lacks any community traction or ecosystem. From a competitive standpoint, it represents a 'snapshot' of research from the mid-pandemic era. The defensibility is near zero because the code serves primarily to validate the paper's findings rather than providing a maintainable tool or platform. While the approach of using RL for NPI optimization was novel during the COVID-19 peak, the space is now crowded with more sophisticated models from institutions like IHME or Imperial College. Frontier labs (OpenAI/Anthropic) are unlikely to build this directly, as the market for pandemic policy optimization is limited to niche governmental and academic bodies. However, the methodology itself is easily reproducible by any competent data science team using modern RL libraries. The 'displacement horizon' is short because the specific parameters and assumptions of a 2021-era COVID model are already outdated by newer variants and changed social dynamics.