atlas

Research map / Multi-agent systems and games / Games and equilibria

Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers

ICML 2021 · Multi-agent systems and games › Games and equilibria · approach: Learning in Markov games · 3 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
Use maximum Gini correlated equilibrium (MGCCE) as the JPSRO meta-solver instead of uniform, alpha-Rank, PRD, or random solversJPSRO(CCE) meta-solver · Kuhn Poker (3-player)CCE Gap Sum (under MWCCE)Helped
Use a CCE meta-solver (CCE-based MS variants) in JPSRO instead of traditional PSRO meta-solversJPSRO on Trade Comm · Trade Comm (3-item, common payoff)Value sum (under MWCCE)Helped
Use the approximate CCE meta-solver (approx-eps MGCCE) in JPSRO (ablation)JPSRO on Trade Comm · Trade Comm (3-item, common payoff)convergence to optimal value sumHurt
Use JPSRO with a CCE meta-solver on SheriffJPSRO on Sheriff · Sheriff (2-player general-sum)value sum (under MWCCE)Helped
Use random-vertex CCE meta-solver (RVCCE) for exploration in JPSROJPSRO · generalqualitative exploration/valueHelped

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