Home▸AI & Machine Learning▸Monte Carlo Tree Search Explained

🌲 Monte Carlo Tree Search Explained

Interactive 3D game-tree visualization showing Monte Carlo Tree Search building out a decision tree move by move, with adjustable exploration constant (UCB1 C) and simulation-count sliders to watch selection, expansion, simulation and backpropagation unfold live.

AI & Machine Learning3DModerate60 FPS

A 3D game-decision tree grows outward from a purple root node, one Monte Carlo Tree Search iteration at a time — watch selection, expansion, simulation and backpropagation update node sizes and colours live.

🔬 What It Demonstrates

Each iteration walks down the tree using the UCB1 formula to balance exploring untried moves against exploiting known-good ones, adds one new node, runs random rollouts, and carries the result back up every visited node.

🎮 How to Use

Adjust the exploration constant, rollout count and branching factor, then press Step to watch a single iteration unfold, or set an auto-play speed to let the tree grow on its own. Node size tracks visit count; colour tracks win-rate.

💡 Did You Know?

MCTS powers DeepMind's AlphaGo and AlphaZero, letting them search game trees far too large to explore exhaustively by focusing computation on the branches most likely to matter.

⚙ Under the hood

monte-carlo-tree-searchgame-aireinforcement-learningucb1search-treesdecision-makingalgorithms

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install