Reinforcement Learning for Safe Occupancy Strategies in Educational Spaces during an Epidemic

Abstract

Epidemic modeling, encompassing deterministic and stochastic approaches, is vital for understanding infectious diseases and informing public health strategies. This research adopts a prescriptive approach, focusing on reinforcement learning (RL) to develop strategies that balance minimizing infections with maximizing in-person interactions in educational settings. We introduce SafeCampus , a novel tool that simulates infection spread and facilitates the exploration of various RL algorithms in response to epidemic challenges. SafeCampus incorporates a custom RL environment, informed by stochastic epidemic models, to realistically represent university campus dynamics during epidemics. We evaluate Q-learning for a discretized state space which resulted in a policy matrix that not only guides occupancy decisions under varying epidemic conditions but also illustrates the inherent trade-off in epidemic management. This trade-off is characterized by the dilemma between stricter measures, which may effectively reduce infections but impose less educational benefit (more in-person interactions), and more lenient policies, which could lead to higher infection rates.