AAAI Publications, Seventh Artificial Intelligence and Interactive Digital Entertainment Conference

Font Size: 
An Object-Oriented Approach to Reinforcement Learning in an Action Game
Shiwali Mohan, John E. Laird

Last modified: 2011-10-09

Abstract


In this work, we look at the challenge of learning in an action game,Infinite Mario. Learning to play an action game can be divided intotwo distinct but related problems, learning an object-relatedbehavior and selecting a primitive action. We propose a framework that allows for the use of reinforcement learning for both ofthese problems. We present promising results in some instances of thegame and identify some problems that might affect learning.

Full Text: PDF