Mixture of Expert Used to Learn Game Play

Authors:
Peter Lacko;Vladimír Kvasnička
Affiliations:
Institute of Applied Informatics Faculty of Informatics and Information technologies, Slovak University of Technology, Bratislava 842 16;Institute of Applied Informatics Faculty of Informatics and Information technologies, Slovak University of Technology, Bratislava 842 16
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 6
Cited 0

Practical Issues in Temporal Difference Learning

Machine Learning
TD-Gammon, a self-teaching backgammon program, achieves master-level play

Neural Computation
Temporal difference learning and TD-Gammon

Communications of the ACM
Modular and hierarchical learning systems

The handbook of brain theory and neural networks
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Learning to Predict by the Methods of Temporal Differences

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by a backtrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feed-forward neural networks that are adapted by reinforcement temporal difference TD(茂戮驴) technique. We study standard feed-forward networks and mixture of adaptive experts networks. As a test game, we used the game of simplified checkers. It is demonstrated that both networks are capable of game strategy emergence.