atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games

ICML 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Zero-sum game learning dynamics · 5 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Initialize restricted game with CTME-based strategies and terminate early using CTME utility (CISGT vs ISGT) (ablation)ISG for TMEs · Network security grid, 5x5 and largerruntime (s)Helped
Use CISGT instead of FullTME (enumerating all pure strategies)TME computation · Network security grid 5x5 (p=0.8,q=0.6)runtime (s): FullTME out of memory vs 9.8sHelped
Vanilla-ISG (NE convergence) instead of TME-aware ISG (ablation)CTME/NE computation in ISG · Network security grid 4x4 (p=0.4,q=0.2)team utility gap relative to CISGT: 35% gapHurt
TMSP transformation of CTME (TMSP-Alg) instead of computing TME (ablation)TME approximation from CTME · Network security grid 4x4 (p=0.4,q=0.2)team utility gap relative to CISGT: 61% gapHurt
Vanilla-ISG (no TME-aware operations) in multiplayer gamesISG · Three-player theoretical exampleconvergence to TMEHurt

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