Reinforcement Learning / 2026

Modeling Infectious Disease Outbreak for Optimal Government Intervention

Formulated a multi-city epidemic control policy by modeling pandemic response as a Markov Decision Process solved with Reinforcement Learning, balancing healthcare pressure, economic impact, policy actions, and long-horizon intervention outcomes.

Reinforcement LearningMarkov Decision ProcessesStable-Baselines3Policy Evaluation

This project modeled infectious disease response as a decision-making problem where interventions affect both public health and economic outcomes over time. The work defined the state and action structure, evaluated policies through Bellman-style value computation, and compared deep reinforcement learning agents such as PPO, A2C, and DQN against exact baselines.