AI Paper Atlas

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

Computing Equilibrium beyond Unilateral Deviation

Mingyang Liu, Gabriele Farina, Asuman E. Ozdaglar

ICLR 2026 · Learning theory and algorithms › Submodular and game algorithms · approach: Correlated equilibria in sequential games · 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
compute MASE instead of Nash/CCE with no-regret baselinesPrisoner's Dilemma · Prisoner's Dilemmasocial welfare: 0.4 -> 1.0Improved
compute MASE instead of Nash equilibrium baselinesStag Hunt · Stag Huntequilibrium selectedImproved
allow exploitability to rise from 0.0 to 0.1MASE · Prisoner's Dilemmasocial welfare: 0.4 -> 1.0Improved
use MASE instead of baselines for unilateral exploitabilitynormal-form games · unilateral exploitabilityexploitabilityNo clear effect
increase game size (players, actions) for no-regret baselinesFTRL/Hedge/FTPL/OMD · random normal-form and polymatrix games, coalitions up to size twocoalition exploitabilityHurt

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