AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Structure-Induced Information for Rerooting Levin Tree Search

Jake Tuero, Michael Buro, Laurent Orseau, Levi Lelis

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 0 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
use a rerooter (√LTS-LH) instead of plain LTS during online bootstrap trainingLTS · BoulderDash hard testproblems solved: 10 -> 100 solvedImproved
add heuristic-based rerooting (√LTS-H) in place of subgoal-conditioned policy (PHS*(πSG)) when dirt reaches 20%BoulderDash training · BoulderDash 20% dirttraining expansions: 299,672,516 -> 19,866,165Improved
increase dirt fraction in BoulderDash to 30% or morePHS*(πSG) · BoulderDash trainingtraining problems solved: 10,000 -> 11 (30%), no progress at 40%/50%Hurt
increase dirt fraction to 50%√LTS-L · BoulderDash trainingtraining problems solved: 9,998 -> 605 (10% -> 50%)Hurt
add heuristic signal to clustering rerooter (√LTS-LH vs √LTS-L) (ablation)√LTS-L · CraftWorld hard testexpansions: 8,802.62 -> 1,347.52Improved
add clustering signal to heuristic rerooter (√LTS-LH vs √LTS-H) (ablation)√LTS-H · CraftWorld hard testexpansions: 2,514.62 -> 1,347.52Improved
add clustering signal to heuristic rerooter (√LTS-LH vs √LTS-H) (ablation)√LTS-H · Sokoban testexpansions: 2,626.82 -> 1,736.03Improved
add clustering signal to heuristic rerooter (√LTS-LH vs √LTS-H) (ablation)√LTS-H · BoulderDash 30% dirt trainingtraining expansions: 27,965,657 -> 57,780,467Hurt
add clustering signal to heuristic rerooter (√LTS-LH vs √LTS-H) (ablation)√LTS-H · BoulderDash hard testexpansions: 92.37 -> 92.68No clear effect
replace subgoal generation with clustering-based rerooting (√LTS-L vs LTS(πSG))LTS(πSG) · BoulderDash hard testexpansions: 202.38 -> 131.18Improved
use rerooting instead of PHS*(πSG) on TSP and Sokoban testPHS*(πSG) · TSP (GridWorld) testexpansions: 46.31 -> 55.44 (√LTS-H)Hurt
use heuristic rerooter instead of WA*WA*(1.5) · Sokoban testexpansions: 1,201.03 -> 2,626.82Hurt

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