Symbol Acquisition for Probabilistic High-Level Planning / 3619
George Konidaris, Leslie Kaelbling, Tomas Lozano-Perez
We introduce a framework that enables an agent to autonomously learn its own symbolic representation of a low-level, continuous environment. Propositional symbols are formalized as names for probability distributions, providing a natural means of dealing with uncertain representations and probabilistic plans. We determine the symbols that are sufficient for computing the probability with which a plan will succeed, and demonstrate the acquisition of a symbolic representation in a computer game domain.