Temporal Difference Learning of Position Evaluation in the Game of Go

@inproceedings{Schraudolph1993TemporalDL,
  title={Temporal Difference Learning of Position Evaluation in the Game of Go},
  author={Nicol N. Schraudolph and Peter Dayan and Terrence J. Sejnowski},
  booktitle={NIPS},
  year={1993}
}
The game of Go has a high branching factor that defeats the tree search approach used in computer chess, and long-range spatiotemporal interactions that make position evaluation extremely difficult. Development of conventional Go programs is hampered by their knowledge-intensive nature. We demonstrate a viable alternative by training networks to evaluate Go positions via temporal difference (TD) learning. Our approach is based on network architectures that reflect the spatial organization of… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 92 extracted citations

Computer Go: An AI oriented survey

Artif. Intell. • 2001
View 11 Excerpts
Highly Influenced

Go, Svm, Go

GoThore, Graepel, +3 authors HerbrichComputer
2000
View 4 Excerpts
Highly Influenced

Evolutionary Methods for Learning No-limit Texas Hold ’ Em Poker

Gikunju Joseph, Nicolai Regina, Saskatchewan
2008
View 4 Excerpts
Highly Influenced

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Practical issues in temporal difference learning

Machine Learning • 1991
View 4 Excerpts
Highly Influenced

Wally , a Go playing program

W. H. Newman
1988
View 9 Excerpts
Highly Influenced

Wally, a Go playing program. Shareware C program available by Internet anonymous file transfer from bsdserver.ucsf.edu, file Go/comp/wally.sh.Z

W. H. Newman
1988
View 4 Excerpts
Highly Influenced

Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence • 1984
View 3 Excerpts
Highly Influenced

MIT Press, forthcoming

R Rivest
Invited talk: Computational Learning Theory and Natural Learning Systems, • 1993
View 2 Excerpts

Monte Carlo Go. Manuscript available by Internet anonymous file transfer from bsdserver.ucsf.edu, file Go/comp/mcgo.tex.Z

B. Brugmann
1993
View 2 Excerpts

Carbon versus silicon: Matching wits with TD-Gammon

B. Robertie
Inside Backgammon, • 1992
View 2 Excerpts

Similar Papers

Loading similar papers…