An Object-Oriented Approach to Reinforcement Learning in an Action Game
DOI:
https://doi.org/10.1609/aiide.v7i1.12451Keywords:
decision making, reinforcement learning, action gamesAbstract
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.
Downloads
Published
2011-10-09
How to Cite
Mohan, S., & Laird, J. (2011). An Object-Oriented Approach to Reinforcement Learning in an Action Game. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 7(1), 164-169. https://doi.org/10.1609/aiide.v7i1.12451
Issue
Section
Poster Papers