MCTS (Tree Search)

← Back to the article

MCTS explores possible future moves by trying many pretend games.

What it does

MCTS explores possible future moves by trying many pretend games.

Simulation: Mental practice game • Roll-out: Playing to the end

How it works

  • Pick a possible move.
  • Simulate what might happen after that move.
  • Choose moves that looked good in many simulations.

Uses and applications

  • A board game AI can choose a smart move.
  • A planning tool can compare possible next steps.
  • A robot can test possible paths in a simulation before moving.

In short

MCTS is closely linked to AlphaGo and game search.

Related methods

  • AlphaGo: Combined MCTS with learned networks to play Go.
  • AlphaZero: Uses MCTS guided by a network trained through self-play.
  • A* Search: Searches for a path to a goal rather than sampling future games.

Back to Reinforcement learning, agents and planning · All topics

The interactive demonstration and the Python walkthrough for this topic need JavaScript.