Investigations on Improvised Neural Network
Chess Engine for Augmenting Topologies

M Suresh Babu; E. Keshava Reddy

doi:https://doi.org/10.14445/22315373/IJMTT-V48P530

International Journal of Mathematics Trends and Technology

Research Article | Open Access | Download PDF

Volume 48 | Number 3 | Year 2017 | Article Id. IJMTT-V48P530 | DOI : https://doi.org/10.14445/22315373/IJMTT-V48P530

Investigations on Improvised Neural Network Chess Engine for Augmenting Topologies

M Suresh Babu, E. Keshava Reddy

Citation :

M Suresh Babu, E. Keshava Reddy, "Investigations on Improvised Neural Network Chess Engine for Augmenting Topologies," International Journal of Mathematics Trends and Technology (IJMTT), vol. 48, no. 3, pp. 214-217, 2017. Crossref, https://doi.org/10.14445/22315373/IJMTT-V48P530

Abstract

In this paper, reinforcement learning in a chess engine with the help of genetic algorithm was investigated. Thereinforcement learning methodology is used in the chess engine to get trained in to play games. The engine initially starts with null information about the game, however, every further moves in the game gets stored within the chess engine. Hencechess engine gains experience to discharge best performance with continuing games. The engine uses temporal difference leaf learning approach to improve the skill set in every level. The engine performs a brute force search of all possible positions that result from the given position on the board. The positions are evaluated using an evaluation function. The evaluation function incorporated with present engine is a neural network which returns a value for each position indicating its potential for either black or white. The neural network learns the function whose values are provided by the temporal difference leaf learning algorithm.

Keywords

Reinforcement Learning, Gene Chess Engine, NEAT, Neural Network.

References

[1]. Kenneth O. Stanley,Risto, Miikkulainen, Evolving Neural Networks through Augmenting Topologies, 10(2):99-127, 2002
[2]. Sebastian Thrun , Learning To Play the Game of Chess. Advances in Neural Information Processing Systems 7 1995.
[3]. HenkMannen, October 2003, Learning To Play Chess Using Reinforcement Learning With Database Games.
[4]. Philipp Koehn, 1994, Combining Genetic Algorithms and Neural Networks: The Encoding Problem.
[5]. PetrAksenov, 2008, Genetic algorithms for optimizing chess position scoring.
[6]. Jonathan Baxter, Andrew Tridgell ,LexWeaver ―KnightCap: A chess program that learns by combining TD(λ) with game-tree search ” , CiteSeerXβ 5 Jan 1999.
[7]. David B. Fogel, Evolving an Expert Checkers Playing Program, Published in IEEE August 2001.
[8]. A. L. Samuel, ―Some studies in machine learning using the game of checkers,‖IBMRes. Dev., vol. 3, pp. 210-219, 1959.
[9] Evaluation of chess position by Modular Neural Network generate by genetic algorithm,7th European conference, EuroGP 2004,Coimbra,Portugal,April 2004
[10]. David b. Fogel, fellow, ieee, Timothy j. hays, Sarah l. hahn, and James quon, A Self-Learning Evolutionary Chess Program, IEEE-2004.
[11]. by Simon M. Lucas, Computational Intelligence and Games: Challenges and Opportunities. International Journal of Automation and Computing (2008), volume 5, pages: 45 – 57.
[12]. AI Techniques For Game Programming, 2002, Prima Tech.ISBN-13: 978-1931841085.