Paper 13051-45
Modeling adversary behavior using Q-Learning
25 April 2024 • 11:10 AM - 11:30 AM EDT | Potomac 4
Abstract
This project explores the application of reinforcement learning and game theory principles in modeling
strategic interactions within a conflict scenario. A Q-learning algorithm is developed to optimize
decision-making by learning from rewards and risks associated with different actions. The
analysis involves tracking the learning progress, evaluating the effectiveness of learned policies, and
testing the algorithm’s performance under varying consequences. Results indicate that incorporating
risk values into the Q-learning process enhances decision quality. Next, game theory is employed
to create a strategic interaction between an agent and an adversary. The agent strategically
manipulates the adversary’s decisions by altering risk values associated with potential actions. Findings
demonstrate the agent’s ability to influence the adversary’s choices, reduce their cumulative
reward, and introduce delays in the adversary’s decision-making. This experiment sheds light on
the dynamic interplay between reinforcement learning and strategic manipulation, offering insights
into decision-making processes within complex environments.