AI Paper Atlas

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

VAST: Value Function Factorization with Variable Agent Sub-Teams

Thomy Phan, Fabian Ritz, Lenz Belzner, Philipp Altmann, Thomas Gabor, Claudia Linnhoff-Popien

NeurIPS 2021 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Value factorization · 11 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 VAST with QTRAN operator and meta-gradient assignment instead of flat QTRAN/QMIX/ILVAST(QTRAN, MetaGrad) · Warehouse[16]completed orders (training curve)Improved
VAST instead of flat QMIX/QTRANVAST · Battle[80]kill countImproved
VAST instead of flat QMIX/QTRAN/ILVAST · GaussianSqueeze[800]system performanceImproved
VAST(eta=1/2) instead of QTRAN in small instanceVAST · Warehouse[4]completed ordersHurt
VAST instead of flat VFF in small instanceVAST · GaussianSqueeze[200]system performanceNo clear effect
VFF operator QTRAN instead of IL/VDN/QMIX inside VAST (ablation)VAST · Warehouse[4], Battle[20]performanceImproved
vary VFF operator inside VAST (ablation)VAST · GaussianSqueeze[200]system performanceNo clear effect
add VAST sub-teams to IL (VAST(IL) vs IL)IL · Warehouse[4], Battle[20], GaussianSqueeze[200]learning stabilityImproved
sub-team ratio eta 1/4 instead of 1/2 (ablation)VAST · Warehouse[16], GaussianSqueeze[800]performance over trainingImproved
sub-team ratio eta 1/2 instead of 1/4 (ablation)VAST · Battle[80]kill countImproved
MetaGrad assignment instead of Random/Fixed/Spatial (ablation)VAST(QTRAN, eta=1/4) · Warehouse[16], Battle[80], GaussianSqueeze[800]performanceImproved
Fixed assignment instead of MetaGrad (ablation)VAST · Battle[80]kill countNo 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