Agent Decompositions in Reinforcement Learning Architectures

Authors

Nancy Owens Fulda, Brigham Young University
Todd Peterson, Brigham Young University

Keywords

agent decompositions, reinforcement learning architectures, learning speed

College

Physical and Mathematical Sciences

Department

Computer Science

Abstract

Reinforcement learning is a sub-discipline of machine learning in which an autonomous program, called an agent, learns to behave appropriately in its environment. Appropriate behavior is described in terms of numerical reinforcements which the agent receives for appropriate or inappropriate actions. By storing a running average of the reinforcements received for given actions in given situations, the agent learns which behaviors are most desirable.

Recommended Citation

Fulda, Nancy Owens and Peterson, Todd (2014) "Agent Decompositions in Reinforcement Learning Architectures," Journal of Undergraduate Research: Vol. 2014: Iss. 1, Article 1189.
Available at: https://scholarsarchive.byu.edu/jur/vol2014/iss1/1189