Computing Atlas

How Computing Was Built
Sign In
Text size
100%
Theme
Algorithm

Monte Carlo Tree Search

Machine Learning Algorithm

Monte Carlo tree search (MCTS) is a heuristic tree search algorithm for decision processes, most notably the kind of turn-based decision a board game presents, that builds a search tree by repeatedly sampling random playouts from promising positions rather than exhaustively evaluating every branch. Combined with deep neural networks from 2016 onward, MCTS became the core search method behind program victories in games such as Go, Chess and Shogi, and it is also used in turn-based strategy video games and other decision applications outside of games. This description is adapted from Wikipedia contributors under CC BY-SA 4.0; changes were made. https://creativecommons.org/licenses/by-sa/4.0/

Facts
Credited To
Remi Coulom (2006), who coined the name; UCT variant by Levente Kocsis and Csaba Szepesvari 1
Classification
Design Technique
Heuristic or Approximation 1
Sources
1. Wikipedia: Monte Carlo Tree Search
Wikimedia Foundation
  • Lead section
    In computer science, Monte Carlo tree search (MCTS) is a heuristic tree search algorithm for some kinds of decision processes, most notably those employed in software that plays board games. In that context MCTS is used to solve the game tree.
  • History
    In 2006, inspired by its predecessors, Rémi Coulom described the application of the Monte Carlo method to game-tree search and coined the name Monte Carlo tree search.
  • entity record, description (design-technique)
    Monte Carlo tree search (MCTS) is a heuristic tree search algorithm for decision processes, most notably the kind of turn-based decision a board game presents, that builds a search tree by repeatedly sampling random playouts from promising positions rather than exhaustively evaluating every branch.
View the Source
Comments (0)
No comments yet. Be the first to share a thought.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.