A self-learning evolutionary chess program
Authors:
- 1 December 2004
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 92 (12) , 1947-1954
Abstract
A central challenge of artificial intelligence is to create machines that can learn from their own experience and perform at the level of human experts. Using an evolutionary algorithm, a computer program has learned to play chess by playing games against itself. The program learned to evaluate chessboard configurations by using the positions of pieces, material and positional values, and neural networks to assess specific sections of the chessboard. During evolution, the program improved its play by almost 400 rating points. Testing under simulated tournament conditions against Pocket Fritz 2.0 indicated that the evolved program performs above the master level.Keywords
This publication has 15 references indexed in Scilit:
- Draw in BahrainScience, 2002
- Evolving an expert checkers playing program without using human expertiseIEEE Transactions on Evolutionary Computation, 2001
- If You Build It, Will It Know?Science, 2000
- Evolutionary checkersNature, 1999
- Evolution, neural networks, games, and intelligenceProceedings of the IEEE, 1999
- AI as SportScience, 1997
- Practical issues in temporal difference learningMachine Learning, 1992
- Tree Searching Algorithms1990
- Chess-Playing Programs and the Problem of ComplexityIBM Journal of Research and Development, 1958
- XXII. Programming a computer for playing chessJournal of Computers in Education, 1950