•  
  •  
 

Journal of Undergraduate Research

Keywords

automatic sensor, action selection, Q-learning, RBF networks

College

Physical and Mathematical Sciences

Department

Computer Science

Abstract

Continuous state spaces can be quite useful in Q-learning. Many real world problems are simply not discrete. An attempt to represent continuous values using a discrete state space is inherently problematic, as the selected level of discritization will likely be imperfect and unable to adapt to change. Such problems thus favor a continuous representation of the state space. Continuous state spaces, however, introduce new difficulties. They are infinitely large, and Q-learning is no longer guaranteed to converge.

Share

COinS