Research map / Learning theory and algorithms / Submodular and game algorithms
Safe Search for 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 |
|---|---|---|---|
| Apply safe subgame search instead of the blueprint | Stackelberg solving for two-stage games · Two-stage games with large subgames (M=m=100) | leader payoff: 1.1730 -> 1.6696 | Helped |
| Use full-game solving rather than safe search | Stackelberg solving for two-stage games · Two-stage games with large subgames (M=m=100) | leader payoff: 1.6696 -> 1.3125 | Hurt |
| Apply safe search rather than the blueprint | Stackelberg solving for Goofspiel · Goofspiel (n=5, m=4) | leader utility: 5.03 -> 5.29 | Helped |
| Apply safe search rather than the blueprint | Stackelberg solving for Leduc Hold'em · Leduc Hold'em (n=8 cards) | leader payoff: -0.1670 -> -0.1609 | Helped |
| Use full-game solving rather than safe search | Stackelberg solving for Leduc Hold'em · Leduc Hold'em (n=4 cards) | leader payoff: -0.1862 -> -0.1882 | Hurt |
| Set bound-splitting α to different tested values (ablation) | Safe search · Goofspiel (n=5, m=4) | leader payoff: 5.32, 5.34, 5.29, 5.31, 5.30 | No clear effect |
| Lower bound-splitting α (ablation) | Safe search · Leduc Hold'em (n=4 cards) | leader payoff: -0.184 -> -0.189 | Helped |
| Increase slack multiplier β from 1 to 4 (ablation) | Safe search · Goofspiel (n=5, m=4) | leader payoff: 5.29 -> 5.55 | Helped |
| Increase slack multiplier β from 4 to 16 (ablation) | Safe search · Goofspiel (n=5, m=4) | leader payoff: 5.55 -> 5.50 | Hurt |
| Increase slack multiplier β from 4 to 8 (ablation) | Safe search · Leduc Hold'em (n=4 cards) | leader payoff: -0.178 -> -0.212 | Hurt |
Closest papers by meaning
- Robust Stackelberg Equilibria in Extensive-Form Games and Extension to Limited Lookahead (AAAI 2018 · similarity 0.92)
- Using Correlated Strategies for Computing Stackelberg Equilibria in Extensive-Form Games (AAAI 2016 · similarity 0.91)
- Double-Oracle Sampling Method for Stackelberg Equilibrium Approximation in General-Sum Extensive-Form Games (AAAI 2020 · similarity 0.90)
- Stackelberg Planning: Towards Effective Leader-Follower State Space Search (AAAI 2018 · similarity 0.90)
- Regret Minimization in Stackelberg Games with Side Information (NeurIPS 2024 · similarity 0.87)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.87)
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.