As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In this work, we analyze and improve upon reinforcement learning techniques used to build agents that can learn to play Infinite Mario, an action game. We use the object-oriented representation with the hierarchical RL model as a learning framework. We then extend the idea of hierarchical RL by designing a hierarchy in action selection using domain specific knowledge. Using experimental results, we show that this approach facilitates faster and efficient learning for the domain.