Learning a Strategy with Neural Approximated Temporal-Difference Methods in English Draughts

Creators:	Faußer, Stefan A. and Schwenker, Friedhelm
Title:	Learning a Strategy with Neural Approximated Temporal-Difference Methods in English Draughts
Item Type:	Conference or Workshop Item
Event Title:	(Proceedings of the) 20th International Conference on Pattern Recognition (ICPR)
Event Location:	Istanbul, Turkey
Event Dates:	August, 23-26, 2010
Page Range:	pp. 2925-2928
Date:	2010
Divisions:	Informationsmanagement
Abstract (ENG):	Having a large game-tree complexity and being EXPTIME-complete, English Draughts, recently weakly solved during almost two decades, is still hard to learn for intelligent computer agents. In this paper we present a Temporal-Difference method that is nonlinear neural approximated by a 4-layer multi-layer perceptron. We have built multiple English Draughts playing agents, each starting with a randomly initialized strategy, which use this method during self-play to improve their strategies. We show that the agents are learning by comparing their winning-quote relative to their parameters. Our best agent wins versus the computer draughts programs Neuro Draughts, KCheckers and CheckerBoard with the easych engine and looses to Chinook, GuiCheckers and CheckerBoard with the strong cake engine. Overall our best agent has reached an amateur league level.
Forthcoming:	No
Language:	English
Citation:	Faußer, Stefan A. and Schwenker, Friedhelm (2010) Learning a Strategy with Neural Approximated Temporal-Difference Methods in English Draughts. In: (Proceedings of the) 20th International Conference on Pattern Recognition (ICPR), August, 23-26, 2010, Istanbul, Turkey, pp. 2925-2928. ISBN 9781424475421

Actions for admins (login required)

View Item in edit mode