Learning of Piece Values for Chess Variants
@inproceedings{Droste2008LearningOP, title={Learning of Piece Values for Chess Variants}, author={Sacha Droste and J. F{\"u}rnkranz}, year={2008} }
In this paper we describe a set of experiments for learning a the values of chess pieces for the popular chess variants crazyhouse, suicide, and atomic chess. We follow an established methodology that relies on reinforcement learning from self-games to learn piece values and piece-square tables for these chess variants. The learned piece values are quite different from those of standard chess, and in several ways surprising, but they generally outperform those that have been previously used in… CONTINUE READING
Figures, Tables, and Topics from this paper
3 Citations
References
SHOWING 1-10 OF 34 REFERENCES
Experiments in Parameter Learning Using Temporal Differences
- Computer Science
- J. Int. Comput. Games Assoc.
- 1998
- 45
- PDF
KnightCap: A Chess Programm That Learns by Combining TD(lambda) with Game-Tree Search
- Computer Science, Mathematics
- ICML
- 1998
- 78
- PDF
First Results from Using Temporal Difference Learning in Shogi
- Computer Science
- Computers and Games
- 1998
- 26
TDLeaf(lambda): Combining Temporal Difference Learning with Game-Tree Search
- Computer Science
- ArXiv
- 1999
- 29
- Highly Influential
- PDF
Temporal difference learning applied to game playing and the results of application to Shogi
- Computer Science
- Theor. Comput. Sci.
- 2001
- 23
Some studies in machine learning using the game of checkers. II: recent progress
- Computer Science
- 1967
- 583
- Highly Influential
Some Studies in Machine Learning Using the Game of Checkers
- Computer Science
- IBM J. Res. Dev.
- 1959
- 2,204
- PDF