AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

An Analysis of Monte Carlo Tree Search

Steven James, George Konidaris, Benjamin Rosman

AAAI 2017 · Learning theory and algorithms › Combinatorial and search optimization · approach: Monte Carlo tree search · 52 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase Lipschitz constant (less smooth transitions) (ablation)uniformly random rollout policy · 10x10 grid worldfraction of states with optimal actionHurt
increase noise std of simulated leaf values (ablation)UCT · ternary tree height 10probability of correct action orderingHurt
use low-variance rollouts with incorrect bias instead of uniform random (ablation)UCT · [5,5] k-ary tree, 30 iterationscorrect action rateHurt
use rollouts peaked about the optimal action instead of uniform random (ablation)UCT · [5,5] k-ary treecorrect action rateImproved
use heavy rollout (optimal action with prob 0.6) instead of uniform random (ablation)UCT · [5,10] k-ary treecorrect action rateImproved
use high-variance rollouts with large std (ablation)UCT · [5,5] k-ary treecorrect action rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy