AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Learning Multi-Agent Coordination via Sheaf-ADMM

Jeffrey Seely, Bartłomiej Cupiał, Llion Jones

ICML 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Coordination graphs · 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 ADMM coordination iterations (K=0 -> K=20) (ablation)Sheaf-ADMM · Sudokusolved rate (%): 0.0% -> 92.5%Improved
use learned shared restriction maps instead of identity maps (ablation)Sheaf-ADMM · Sudokusolved rate (%): 6.1% -> 92.5%Improved
add LoRA modulation of restriction maps to shared maps (ablation)Sheaf-ADMM · Mazesolved rate (%): 8.9% -> 99.8%Improved
add LoRA modulation of restriction maps to shared maps (ablation)Sheaf-ADMM · Sudokusolved rate (%): 92.5% -> 87.5%Hurt
add l1 regularization to the diagonal quadratic x-update objective (ablation)Sheaf-ADMM · Sudokusolved rate (%): 47.0% -> 92.5%Improved
make the quadratic term learned (diagonal quad vs fixed Q) (ablation)Sheaf-ADMM · Mazesolved rate (%): 38.9% -> 99.2%Improved
x-update variants on MNIST (fixed Q vs quad vs quad + l1) (ablation)Sheaf-ADMM · MNISTaccuracy: 98.4% -> 98.2% -> 98.5%No clear effect
use conjugate gradient instead of GD + Nesterov for the z-update (ablation)Sheaf-ADMM · Sudokusolved rate (%): 0.0% -> 92.5%Improved
use conjugate gradient instead of GD + Nesterov for the z-update (ablation)Sheaf-ADMM · MNISTaccuracy: 52.2% -> 98.5%Improved
use conjugate gradient instead of GD + Nesterov for the z-update (ablation)Sheaf-ADMM · Mazesolved rate (%): 98.2% -> 99.8%Mixed
increase ADMM iterations from K=10 to K=30 (ablation)Sheaf-ADMM · MNISTaccuracy: 98.5% -> 90.3%Hurt
increase ADMM iterations from K=5 to K=30 (ablation)Sheaf-ADMM · Mazesolved rate (%): 1.2% -> 99.8%Improved

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