Abstract: Q-learning and double Q-learning are well-known sample-based, off-policy reinforcement learning algorithms. However, Q-learning suffers from overestimation bias, while double Q-learning ...
A reinforcement learning framework using Deep Q-Learning to optimize traffic signal timing at intersections. This system uses SUMO (Simulation of Urban MObility) to simulate traffic flow and a neural ...
Abstract: Model-Driven Engineering (MDE) emphasizes models as primary artifacts to enhance abstraction and automation in software development. However, manually defining model transformation rules is ...