Constructing Abstraction Hierarchies Using a Skill-Symbol Loop

09/25/2015

∙

by   George Konidaris, et al.

∙

0

∙

share

We describe a framework for building abstraction hierarchies whereby an agent alternates skill- and representation-acquisition phases to construct a sequence of increasingly abstract Markov decision processes. Our formulation builds on recent results showing that the appropriate abstract representation of a problem is specified by the agent's skills. We describe how such a hierarchy can be used for fast planning, and illustrate the construction of an appropriate hierarchy for the Taxi domain.