Concept · 2 episode(s)

Monte Carlo Tree Search

← all concepts

Definition

Monte Carlo Tree Search grows a search tree by repeatedly rolling out simulated trajectories, expanding nodes that look promising, and using the resulting statistics to pick moves. It’s the algorithm behind AlphaGo and a popular substrate for reasoning-time search in LLMs.

Episodes covering this

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.