atlas

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

Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks

NeurIPS 2019 · Learning theory and algorithms › Submodular and game algorithms · approach: Correlated equilibria in sequential games · 10 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 the subgradient method instead of the LP solverEFCE computation on Battleship · Battleship (3,2), r=3, ship length 1time to violation ≤ 10⁻³: 43m -> 52sHelped
Use the subgradient method instead of the LP solverEFCE computation on Battleship · Battleship (3,2), r=4, ship length 2ability to achieve required accuracyMixed
Use a mediator to coordinate recommendations rather than an unmediated Nash equilibriumBattleship, 3×1 board, γ=2 · Battleshipsocial welfare: -8/9 -> -13/18Helped
Increase cargo capacity from n_max=2 to n_max=5 while keeping r=1Social-welfare-maximizing EFCE · Sheriff baselineSmuggler payoff: 8.00 -> 2.28Hurt
Increase bargaining rounds from r=1 to r=2 at n_max=5Social-welfare-maximizing EFCE · Sheriff baselineSmuggler payoff: 2.28 -> 8.00Helped
Increase bargaining rounds from r=1 to r=3 at n_max=10Social-welfare-maximizing EFCE · Sheriff baselineSmuggler payoff: 1.76 -> 8.00Helped

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