AI Paper Atlas

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

Extreme Value Monte Carlo Tree Search for Classical Planning

Masataro Asai, Stephen Wissow

AAAI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Monte Carlo tree search

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
Replace Gaussian bandit (UCB1-Normal2) with UCB1-UniformGUCT · IPC subset, hFF, 10^4 node evalsinstances solved: 582.95 -> 606.4Improved
Replace UCB1-Normal2 with UCB1-UniformGUCT · IPC subset, hmaxinstances solved: 316.6 -> 455.6Improved
Use Full Bellman backup instead of Monte Carlo backup (ablation)GUCT with UCB1-Normal2 · IPC subset, hFFinstances solved: 582.95 -> 567.2Hurt
Use Full Bellman backup instead of Monte Carlo backup (ablation)GUCT with UCB1-Normal2 · IPC subset, hmaxinstances solved: 316.6 -> 263Hurt
Use Full Bellman backup instead of Monte Carlo backup (ablation)GUCT with UCB1 (base) or UCB1-Normal · IPC subset, hFFinstances solved: 412 -> 459.4; 283.4 -> 318.8Improved
Replace GBFS with GUCT-UniformGBFS · IPC subset, hFFinstances solved: 538 -> 606.4Improved
Replace Softmin-Type(h) with GUCT-UniformSoftmin-Type(h) · IPC subset, hFFinstances solved: 576 -> 606.4Improved
Replace CHK-Uniform (asymptotically optimal) with UCB1-UniformGUCT · IPC subset, hFFinstances solved: 375.4 -> 606.4Improved
Use Max-k bandits instead of UCB1-UniformGUCT · IPC subset, hFFinstances solved: 606.4 -> 162.4 to 267.8Hurt
Use max-of-Gaussians (+) backup instead of Monte Carlo backup (ablation)GUCT-Normal2 · IPC subsetinstances solved: hFF 582.95 -> 578; hmax 316.6 -> 442.4Mixed
Add preferred operators (ablation)GUCT-Uniform · IPC subset, hFFinstances solved: 606.4 -> 635.6Improved
Use GUCT-Uniform instead of GUCT-Normal2 in Fast DownwardGUCT · IPC 2018instances solved: 81.6 -> 80.0No 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