Investigating the Limits of Monte-Carlo Tree Search Methods in Computer Go

  title={Investigating the Limits of Monte-Carlo Tree Search Methods in Computer Go},
  author={Shih-Chieh Huang and Martin M{\"u}ller},
  booktitle={Computers and Games},
Monte Carlo Tree Search methods have led to huge progress in Computer Go. Still, program performance is uneven most current Go programs are much stronger in some aspects of the game, such as local fighting and positional evaluation, than in others. Well known weaknesses of many programs include the handling of several simultaneous fights, including the “two safe groups” problem, and dealing with coexistence in seki. Starting with a review of MCTS techniques, several conjectures regarding the… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 11 references

Fuego-GB Prototype at the human machine competition in Barcelona 2010: a tournament report and analysis

  • M. Müller
  • Technical Report TR 10-08, Dept. of Computing…
  • 2010
3 Excerpts

A Contribution to Reinforcement Learning; Application to Computer-Go

  • S. Gelly
  • PhD thesis, Université Paris-Sud,
  • 2007
1 Excerpt

Similar Papers

Loading similar papers…