Machine Learning and Knowledge Discovery in Databases

Volume 5781 of the series Lecture Notes in Computer Science pp 644-659

Compositional Models for Reinforcement Learning

  • Nicholas K. JongAffiliated withThe University of Texas at Austin
  • , Peter StoneAffiliated withThe University of Texas at Austin

* Final gross prices may vary according to local VAT.

Get Access


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.