Research map / Learning theory and algorithms / Submodular and game algorithms
Using Correlated Strategies for Computing Stackelberg Equilibria in Extensive-Form Games
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 changed | Where | Measured | Effect |
|---|---|---|---|
| compute SSE via correlated-strategy LP with restriction search instead of the MILP with a binary per follower sequence (BC15) | SI-LP/AI-MILP/SI-MILP · Search game depth 6 | runtime (s): 42,261 -> 10,790 | Helped |
| use correlated-strategy algorithm instead of BC15 | SSE solver · Random games, 3e5-3e6 realization plans | games solved within 1s: 2 -> 583 (SI-LP) | Helped |
| restrict all inconsistent information sets (AI-MILP) rather than only shallowest (SI-MILP) (ablation) | MILP-based SSE algorithm · Random games | average runtime | Helped |
| use LP with deterministic-recommendation branching (SI-LP) instead of MILP restrictions (ablation) | SSE algorithm · Random games | average runtime: SI-LP solves 69% under 1s vs 62% AI-MILP, 57% SI-MILP; worst outlier 773s | Mixed |
Closest papers by meaning
- Coarse Correlation in Extensive-Form Games (AAAI 2020 · similarity 0.92)
- Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond (NeurIPS 2020 · similarity 0.92)
- Robust Stackelberg Equilibria in Extensive-Form Games and Extension to Limited Lookahead (AAAI 2018 · similarity 0.92)
- On the Outcome Equivalence of Extensive-Form and Behavioral Correlated Equilibria (AAAI 2024 · similarity 0.90)
- Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games (NeurIPS 2024 · similarity 0.89)
- The Complexity of Correlated Equilibria in Generalized Games (NeurIPS 2025 · similarity 0.88)
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.