Research map / Learning theory and algorithms / Submodular and game algorithms
Computing Ex Ante Coordinated Team-Maxmin Equilibria in Zero-Sum Multiplayer 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 |
|---|---|---|---|
| use the CMB algorithm with hybrid-form strategies and ART | TMECor computation · Kuhn poker and Leduc Hold'em EFGs | runtime: CMB runs several orders of magnitude faster than prior state-of-the-art algorithms | Helped |
| use CMB rather than CMBZ20 | TMECor computation · 5K11 | runtime: 2802s -> 35s | Helped |
| use CMB rather than CMBZ20 | TMECor computation · 6K7 | runtime: 2009s -> 17s | Helped |
| remove associated constraints (ablation) | CMB · 3K4 | runtime: 0.7s -> 2.1s | Hurt |
| remove associated constraints (ablation) | CMB · 3K6 | runtime: 2s -> 20s | Hurt |
| use continuous terminal-reaching variables without ART and BRO (ablation) | CMB · 3K6 | runtime: 2s -> 191s | Hurt |
| replace hybrid-form strategies with joint pure normal-form strategies (ablation) | CMB · 3K6 | runtime: 2s -> 2s | No clear effect |
| combine continuous terminal-reaching variables without ART and joint pure normal-form strategies (ablation) | CMB · 3K6 | runtime: 2s -> 479s | Hurt |
| compute an approximate TMECor with CMB rather than FTP | TMECor computation · 3K5, epsilon=0.01 | runtime: 87s vs 4882s | Helped |
| use coordinated TMECor strategies instead of independent TME strategies | team play · 3K8 | team utility: -0.066 -> -0.019 | Helped |
Closest papers by meaning
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.88)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (NeurIPS 2024 · similarity 0.88)
- The Complexity of Two-Team Polymatrix Games with Independent Adversaries (ICLR 2025 · similarity 0.87)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.87)
- Zero-Sum Games between Mean-Field Teams: Reachability-Based Analysis under Mean-Field Sharing (AAAI 2024 · 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.