Evaluation of Chess Position by Modular Neural Network Generated by Genetic Algorithm

Autonès, Mathieu; Beck, Ariel; Camacho, Philippe; Lassabe, Nicolas; Luga, Hervé; Scharffe, François

doi:10.1007/978-3-540-24650-3_1

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a series of intelligent algorithm have been applied to the automatic parameters adjustment. Such as Genetic Algorithm [4] , Neural Network [4] , Temporal Difference Learning [4,5] (TD) etc. Document [6] introduces a application of Temporal Difference Learning method to adjust the evaluation in 'Backgammon'.…”

Section: The Introduction Of Intelligent Algorithms In Computer Gamementioning

confidence: 99%

An improved algorithm model based on machine learning

Zhou

Huan

et al. 2015

The 27th Chinese Control and Decision Conference (2015 CCDC)

View full text Add to dashboard Cite

In the last decades, Reinforcement Learning (RL) algorithm has attracted more and more attention, and become the research focus in the field of machine learning. This paper leads the typical RL algorithm, Q-learning algorithm, into computer game platform (Connect6), and proposes an improved method. We adjust reward parameter according to the shape of Connect6, and optimize the adjustment of evaluation function to achieve the global optimization. Moreover, the optimization of the reward makes the valueless units away from the evaluation, to reduce the interference of valueless units for optimal results and improve the convergence speed, thereby reducing the overall time of self-learning process.

show abstract

Section: The Introduction Of Intelligent Algorithms In Computer Gamementioning

confidence: 99%

An improved algorithm model based on machine learning

Zhou

Huan

et al. 2015

The 27th Chinese Control and Decision Conference (2015 CCDC)

View full text Add to dashboard Cite

show abstract

“…Over the past years, research in this domain has focused on ways to improve evaluation functions. The most original ones is proposing to optimize the evaluation function using genetic algorithms [9], to replace it by artificial neural networks or to build it automatically using genetic programming [1]. In this perspective, genetic programming [10] has been mainly used in two ways.…”

Section: Introductionmentioning

confidence: 99%

Genetically programmed strategies for chess endgame

Lassabe

Sanchez

Luga

et al. 2006

Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

Classical chess engines exhaustively explore moving possibilities from a chessboard configuration to choose what the next best move to play is. In this article we present a new method to solve chess endgames without using Brute-Force algorithms or endgame tables. We are proposing to use Genetic Programming to combine elementary chess patterns defined by a chess expert. We apply this method specifically to the classical King-Rook-King endgame. We show that computed strategies are both effective and generic for they manage to win against several opponents (human players and artificial ones such as the chess engine CRAFTY). Besides, the method allows to propose strategies that are clearly readable and useable for a purpose such as teaching chess.

show abstract