Sciweavers

Share
PKDD
2009
Springer

Compositional Models for Reinforcement Learning

9 years 2 months ago
Compositional Models for Reinforcement Learning
Abstract. Innovations such as optimistic exploration, function approximation, and hierarchical decomposition have helped scale reinforcement learning to more complex environments, but these three ideas have rarely been studied together. This paper develops a unified framework that formalizes these algorithmic contributions as operators on learned models of the environment. Our formalism reveals some synergies among these innovations, and it suggests a straightforward way to compose them. The resulting algorithm, Fitted R-MAXQ, is the first to combine the function approximation of fitted algorithms, the efficient model-based exploration of R-MAX, and the hierarchical decompostion of MAXQ.
Nicholas K. Jong, Peter Stone
Added 27 May 2010
Updated 27 May 2010
Type Conference
Year 2009
Where PKDD
Authors Nicholas K. Jong, Peter Stone
Comments (0)
books