Memory-guided Exploration in Reinforcement Learning

Authors

James L. Carroll, Brigham Young University
Todd Peterson, Brigham Young University

Keywords

memory-guided exploration, reinforcement learning, Q-learning, Q-value

College

Physical and Mathematical Sciences

Department

Computer Science

Abstract

Traditional reinforcement learning techniques learn a single task by giving the agent positive and negative rewards. In one type of reinforcement learning, called Q-learning, the agent stores Qvalues, which are the expected reward for performing an action in a given state. Task transfer is a method of transferring information learned in one task to another related task. Most work in transfer has focused on classification techniques. The purpose of our research has been to extend classification techniques to reinforcement learning.

Recommended Citation

Carroll, James L. and Peterson, Todd (2014) "Memory-guided Exploration in Reinforcement Learning," Journal of Undergraduate Research: Vol. 2014: Iss. 1, Article 1194.
Available at: https://scholarsarchive.byu.edu/jur/vol2014/iss1/1194