Sufficiency-Based Selection Strategy for MCTS

  title={Sufficiency-Based Selection Strategy for MCTS},
  author={Stefan Freyr Gudmundsson and Yngvi Bj{\"o}rnsson},
Monte-Carlo Tree Search (MCTS) has proved a remarkably effective decision mechanism in many different game domains, including computer Go and general game playing (GGP). However, in GGP, where many disparate games are played, certain type of games have proved to be particularly problematic for MCTS. One of the problems are game trees with so-called optimistic moves, that is, bad moves that superficially look good but potentially require much simulation effort to prove otherwise. Such scenarios… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 29 references

In European Conference on Machine Learning (ECML)

  • Levante Kocsis, Csaba Szepesvári. Bandit based Monte-Carlo planning
  • pages 282–293, Berlin / Heidelberg,
  • 2006
Highly Influential
5 Excerpts


  • David Tolpin, Solomon Eyal Shimony. Mcts based on simple regret
  • abs/1207.5536,
  • 2012
Highly Influential
3 Excerpts


  • Raghuram Ramanujan, Ashish Sabharwal, Bart Selman. On adversarial search spaces, sampling-based planning
  • pages 242–245,
  • 2010
Highly Influential
4 Excerpts

In IJCAI’11 Workshop on General Intelligence in Game Playing Agents (GIGA’11)

  • Hilmar Finnsson, Yngvi Björnsson. Game-tree properties, mcts performance
  • pages 23–30,
  • 2011
2 Excerpts


  • Mesut Kirci, Nathan R. Sturtevant, Jonathan Schaeffer. A GGP feature learning algorithm
  • 25(1):35–42,
  • 2011

Sturtevant , and Jonathan Schaeffer . A GGP feature learning algorithm

  • Mesut Kirci, R. Nathan
  • 2011

The Netherlands

  • Guillaume Chaslot. Monte-Carlo Tree Search. PhD dissertation, Maastricht University
  • Department of Knowledge Engineering,
  • 2010
1 Excerpt

Similar Papers

Loading similar papers…