David Wingate, Vishal Soni, Britton Wolfe, Satinder Singh
Most work on Predictive Representations of State (PSRs) has focused on learning and planning in unstructured domains (for example, those represented by flat POMDPs). This paper extends PSRs to represent relational knowledge about domains, so that they can use policies that generalize across different tasks, capture knowledge that ignores irrelevant attributes of objects, and represent policies in a way that is independent of the size of the state space. Using a blocks world domain, we show how generalized predictions about the future can compactly capture relations between objects, which in turn can be used to naturally specify relational-style options and policies. Because our representation is expressed solely in terms of actions and observations, it has extensive semantics which are statistics about observable quantities.
Subjects: 12.1 Reinforcement Learningn
Submitted: Oct 13, 2006