Research map / Learning theory and algorithms / Submodular and game algorithms
Computing 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 |
|---|---|---|---|
| replace Z-step precision increase with +1 power increase in the iterative algorithm (ablation) | IARAMDT · 4K5 Kuhn poker, eps=1e-3 | runtime: 481s -> 1303s | Hurt |
| add asynchronous precision method (AMDT instead of MDT) (ablation) | IARAMDT · 4K5 Kuhn poker, eps=1e-3 | runtime: 4442s -> 481s | Helped |
| add asynchronous precision method (AMDT instead of MDT) (ablation) | IARAMDT · 4K5 Kuhn poker, eps=1e-4 | runtime: >3h -> 7047s | Helped |
| use +1 power increase instead of Z increase (ablation) | IARAMDT · 4K5 Kuhn poker, eps=1e-2 | runtime: 44s -> 274s | Hurt |
| add associated constraint method (ARAMDT instead of RAMDT) (ablation) | IARAMDT · Kuhn poker, Table 1 | runtime | Helped |
| solve with IARAMDT instead of BARON global solver | TME computation · Kuhn poker, Table 1 | runtime | Helped |
| use TMSP from a CTME instead of directly computed TME | team strategy · 3K4 to 3K7 Kuhn poker | gap to TME value: 88%, 94%, 95%, 92% | Hurt |
Closest papers by meaning
- Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games (ICML 2020 · similarity 0.96)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.89)
- Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Games (ICML 2025 · similarity 0.89)
- 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 0.88)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 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.