Topin, Nicholay
Discovering Subgoals in Complex Domains
desJardins, Marie (University of Maryland, Baltimore County) | Tembo, Tenji (University of Maryland, Baltimore County) | Topin, Nicholay (University of Maryland, Baltimore County) | Bishoff, Michael (University of Maryland, Baltimore County) | Squire, Shawn (University of Maryland, Baltimore County) | MacGlashan, James (Brown University) | Carignan, Rose (University of Maryland, Baltimore County) | Haltmeyer, Nicholas (University of Maryland, Baltimore County)
We present ongoing research to develop novel option discovery methods for complex domains that are represented as Object-Oriented Markov Decision Processes (OO-MDPs) (Diuk, Cohen, and Littman, 2008). We describe Portable Multi-policy Option Discovery for Automated Learning (P-MODAL), an initial framework that extends Pickett and Barto’s (2002) PolicyBlocks approach to OO-MDPs. We also discuss future work that will use additional representations and techniques to handle scalability and learning challenges.