AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search

Jinglong Xiong, Xiaotian Liu, Ruoxin Wang, Zihang Liu, Yefan Zhou, Yujun Yan, Yaoqing Yang

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Probabilistic and autonomous RL · 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
add staged curriculum (full four-stage) instead of direct or partial-curriculum search (ablation)RL4RLA on Newton Sketch · Newton Sketchsuccess rate: 0% -> 100%Improved
skip any intermediate curriculum stage (ablation)RL4RLA · Newton Sketch partial curriculasuccess rate: 100% -> 0%Hurt
replace MCTS with Monte Carlo Graph Search (state merging) (ablation)RL4RLA · Preconditioned Weighted SGDtotal playouts: 34902 -> 10721Improved
replace MCTS with MCGS+UCD (ablation)RL4RLA · Block Randomized Kaczmarztotal playouts: 66468 -> 25158Improved
replace MCTS with MCGS+UCD (ablation)RL4RLA · Subsampled Least Square GDtotal playouts: 15847 -> 5061Improved
replace MCTS with MCGS+UCD (ablation)RL4RLA · Newton Sketchtotal playouts: 2557 -> 1416Improved
use UCD instead of UCT within MCGS (ablation)MCGS · Preconditioned Weighted SGDtotal playouts: 13037 -> 10721Improved
use UCD instead of UCT within MCGS (ablation)MCGS · Newton Sketchtotal playouts: 2682 -> 1416Improved
use UCD instead of UCT within MCGS on simple targets (ablation)MCGS · simple targets (e.g. Landweber iteration)discovery speedNo clear effect
replace MCTS with MCGS on shallow targets (ablation)RL4RLA · shallow targets (Landweber iteration)discovery speedNo clear effect
replace MCTS with MCGS for wall-clock time (ablation)RL4RLA · Subsampled Least Square GDwall-clock time (s): 10.4 -> 8.9Mixed
MCGS success rate vs MCTS on Block Randomized Kaczmarz with UCD (ablation)RL4RLA · Block Randomized Kaczmarzsuccess rate: 75% -> 75%No 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