Learning to evaluate Go positions via temporal difference methods

@inproceedings{Schraudolph2001LearningTE,
  title={Learning to evaluate Go positions via temporal difference methods},
  author={Nicol N. Schraudolph and Peter Dayan and Terrence J. Sejnowski},
  year={2001}
}
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 neural networks to evaluate Go positions via temporal difference (TD) learning. Our approach is based on neural network architectures that reflect the spatial… CONTINUE READING

Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

Citations

Publications citing this paper.
SHOWING 1-10 OF 31 CITATIONS

Reinforcement learning in board games

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Quarto as a Reinforcement Learning problem

  • Frode Stig Nørgaard Pedersen
  • 2019
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND

Systematic selection of N-tuple networks with consideration of interinfluence for game 2048

  • Kiminori Matsuzaki
  • Computer Science
  • 2016 Conference on Technologies and Applications of Artificial Intelligence (TAAI)
  • 2016
VIEW 1 EXCERPT

Temporal difference learning of N-tuple networks for the game 2048

VIEW 1 EXCERPT
CITES BACKGROUND

Design with shape grammars and reinforcement learning

VIEW 1 EXCERPT
CITES BACKGROUND

Evolution of a digital organism playing Go

VIEW 2 EXCERPTS
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 20 REFERENCES

Knowledge representation in the Many Faces of Go

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

All Systems Go

VIEW 1 EXCERPT

To test a powerful computer, play an ancient game," The New York Times, July 29, http://www.cns.nyu. edu/-rnechner/cornpgo/tirnes

  • G. Johnson
  • 1997

Monte Carlo Go," ftp: / /www.joy.ne

  • B. Briigmann
  • jp/welcorne/igs/Go/cornputer/rncgo.tex.Z
  • 1993
VIEW 2 EXCERPTS