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.
Recommended Citation
Fry, Charles Parkinson and Peterson, Todd
(2013)
"Automatic Sensor and Action Selection,"
Journal of Undergraduate Research: Vol. 2013:
Iss.
1, Article 2662.
Available at:
https://scholarsarchive.byu.edu/jur/vol2013/iss1/2662