Research programme › Science policy


COMPUTERS & OPERATIONS RESEARCH; 2008; 35(6):1999 - 2017

Application of reinforcement learning to the game of Othello

Authors: van Eck NJ, van Wezel M
Affiliations: Erasmus Univ

Abstract:
Operations research and management science are often confronted with sequential decision making problems with large state spaces. Standard methods that are used for solving such complex problems are associated with some difficulties. As we discuss in this article, these methods are plagued by the so-called curse of dimensionality and the curse of modelling. In this article, we discuss reinforcement learning, a machine learning technique for solving sequential decision making problems with large state spaces. We describe how reinforcement learning can be combined with a function approximation method to avoid both the curse of dimensionality and the curse of modelling. To illustrate the usefulness of this approach, we apply it to a problem with a huge state space-learning to play the game of Othello. We describe experiments in which reinforcement learning agents learn to play the game of Othello without the use of any knowledge provided by human experts. It turns out that the reinforcement learning agents learn to play the game of Othello better than players that use basic strategies. (c) 2006 Elsevier Ltd. All rights reserved.

Publication type:
Article in Journal

  
Authors (1)
  
Dr. N.J. (Nees Jan) van Eck
Centre for Science and Technology Studies
Researcher. MSc in Economics & Informatics from Erasmus University Rotterdam (2005). Currently working on a PhD thesis on science mapping at Erasmus University Rotterdam. Working at CWTS from November 2008. Involved in various science mapping projects, and working on the development of science ...