ICML-98 Submission #110

Relational Reinforcement Learning

Saso Dzeroski 
Jozef Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia

Luc De Raedt and Hendrik Blockeel
Department of Computer Science, Katholieke Universiteit Leuven
Celestijnenlaan 200A, B-3001 Heverlee, Belgium

Abstract:

Relational reinforcement learning is presented, a learning technique
that combines reinforcement learning with relational learning or
inductive logic programming.  Due to the use of a more expressive
representation language to represent states, actions and Q-functions,
relational reinforcement learning can be potentially applied to a new
range of learning tasks.  One such task that we investigate is
planning in the block's world, where it is assumed that the effects of
the actions are unknown to the agent and the agent has to learn a
policy.  Within this simple domain we show that relational
reinforcement learning solves some existing problems with
reinforcement learning. In particular, relational reinforcement
learning allows to employ structural representations, to make
abstraction of specific goals pursued and to exploit the results of
previous learning phases when addressing new (more complex)
situations.

Keywords: reinforcement learning, relational learning,
inductive logic programming, planning

Email address of contact author: Saso.Dzeroski@ijs.si

Phone number of contact author: ++ 386 61 177 3217

Multiple submission statement: 

This paper is submitted jointly to ICML-98 and ILP-98.