Constructing Abstraction Hierarchies Using a Skill-Symbol Loop [article]

George Konidaris
2015 arXiv   pre-print
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.
arXiv:1509.07582v1 fatcat:he6cxbuyqrfbbn2md7yf6zhusi