A survey of Monte Carlo tree search methods

Cameron B. Browne, Edward Powley, Daniel Whitehouse, Simon M. Lucas, Peter I. Cowling, Philipp Rohlfshagen, Stephen Tavener, Diego Perez, Spyridon Samothrakis, Simon Colton

Research output: Contribution to journalReview ArticleResearchpeer-review

1579 Citations (Scopus)


Monte Carlo tree search (MCTS) is a recently proposed search method that combines the precision of tree search with the generality of random sampling. It has received considerable interest due to its spectacular success in the difficult problem of computer Go, but has also proved beneficial in a range of other domains. This paper is a survey of the literature to date, intended to provide a snapshot of the state of the art after the first five years of MCTS research. We outline the core algorithm's derivation, impart some structure on the many variations and enhancements that have been proposed, and summarize the results from the key game and nongame domains to which MCTS methods have been applied. A number of open research questions indicate that the field is ripe for future work.

Original languageEnglish
Article number6145622
Pages (from-to)1-43
Number of pages43
JournalIEEE Transactions on Computational Intelligence and AI in Games
Issue number1
Publication statusPublished - 1 Mar 2012
Externally publishedYes


  • Artificial intelligence (AI)
  • bandit-based methods
  • computer Go
  • game search
  • Monte Carlo tree search (MCTS)
  • upper confidence bounds (UCB)
  • upper confidence bounds for trees (UCT)

Cite this