A Unifying Framework for Reinforcement Learning and Planning

arXiv (Cornell University)

Abstract

Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both largely have their own research communities. However, if both research fields solve the same problem, then we might be able to disentangle the common factors in their solution approaches. Therefore, this paper presents a unifying algorithmic framework for reinforcement learning and planning (FRAP), which identifies underlying dimensions on which MDP planning and learning algorithms have to decide. At the end of the paper, we compare a variety of well-known planning, model-free and model-based RL algorithms along these dimensions. Altogether, the framework may help provide deeper insight in the algorithmic design space of planning and reinforcement learning.

Authors 4

1. Thomas M. Moerland Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden University , The Netherlands

2. Joost Broekens Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden University , The Netherlands

3. Aske Plaat Aachen Leiden Institute of Advanced Computer Science

   Leiden University

   Affiliation as printed

   Leiden Institute of Advanced Computer Science , Leiden University , The Netherlands

4. Catholijn M. Jonker Aachen Leiden Institute of Advanced Computer Science

   Leiden University · Delft University of Technology

   Affiliation as printed

   Interactive Intelligence , TU Delft , The Netherlands

   Leiden Institute of Advanced Computer Science , Leiden University , The Netherlands