We present an initial proposal for modular object-oriented MDPs, an extension of OO-MDPs that abstracts complex domains that are partially observable and stochastic with multiple goals. Modes reduce the curse of dimensionality by reducing the number of attributes, objects, and actions into only the features relevant for each goal. These modes may also be used as an abstracted domain to be transferred to other modes or to another domain.
This paper describes an architecture for an agent to learn and reason about affordances. In this architecture, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete domain knowledge that includes a representation of affordances as relations defined jointly over objects and actions. Reinforcement learning and decision-tree induction based on this relational representation and observations of action outcomes are used to interactively and cumulatively (a) acquire knowledge of affordances of specific objects being operated upon by specific agents; and (b) generalize from these specific learned instances. The capabilities of this architecture are illustrated and evaluated in two simulated domains, a variant of the classic Blocks World domain, and a robot assisting humans in an office environment.
We review the psychological notion of affordances and examine it anew from a cognitive systems perspective. We distinguish between environmental affordances and their internal representation, choosing to focus on the latter. We consider issues that arise in representing mental affordances, using them to understand and generate plans, and learning them from experience. In each case, we present theoretical claims that, together, form an incipient theory of affordance in cognitive systems. We close by noting related research and proposing directions for future work in this arena.
This paper explores the problem of task learning and planning, contributing the Action-Category Representation (ACR) to improve computational performance of both Planning and Reinforcement Learning (RL). ACR is an algorithm-agnostic, abstract data representation that maps objects to action categories (groups of actions), inspired by the psychological concept of action codes. We validate our approach in StarCraft and Lightworld domains; our results demonstrate several benefits of ACR relating to improved computational performance of planning and RL, by reducing the action space for the agent.
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.