Genetic Algorithms for Evolving Computer Chess Programs
- 9 October 2013
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 18 (5) , 779-789
Abstract
This paper demonstrates the use of genetic algorithms for evolving: 1) a grandmaster-level evaluation function, and 2) a search mechanism for a chess program, the parameter values of which are initialized randomly. The evaluation function of the program is evolved by learning from databases of (human) grandmaster games. At first, the organisms are evolved to mimic the behavior of human grandmasters, and then these organisms are further improved upon by means of coevolution. The search mechanism is evolved by learning from tactical test suites. Our results show that the evolved program outperforms a two-time world computer chess champion and is at par with the other leading computer chess programs.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Expert-driven genetic algorithms for simulating evaluation functionsGenetic Programming and Evolvable Machines, 2010
- Checkers Is SolvedScience, 2007
- Evolution of an Efficient Search Algorithm for the Mate-In-N Problem in ChessLecture Notes in Computer Science, 2007
- GP-EndChess: Using Genetic Programming to Evolve Chess Endgame Players2005
- Evolving an expert checkers playing program without using human expertiseIEEE Transactions on Evolutionary Computation, 2001
- Completely Derandomized Self-Adaptation in Evolution StrategiesEvolutionary Computation, 2001
- Multi-cut αβ-pruning in game-tree searchTheoretical Computer Science, 2001
- Evolution, neural networks, games, and intelligenceProceedings of the IEEE, 1999
- Evolving neural networks to play checkers without relying on expert knowledgeIEEE Transactions on Neural Networks, 1999
- Practical issues in temporal difference learningMachine Learning, 1992