Research map / Learning theory and algorithms / Submodular and game algorithms
Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization
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 team belief DAG (TB-DAG) representation with CFR instead of LP/column generation | adversarial team games · Liar's Dice, Kuhn, Leduc team games (Table 1) | runtime to eps=1e-3 exploitability: generally 2-3 orders of magnitude faster than ZS22 | Helped |
| use TB-DAG CFR instead of single-oracle column generation (ZFCS22) | adversarial team games with high parameters · 3K8, 3K12 | runtime | Hurt |
| use TB-DAG CFR instead of column generation (ZFCS22) | adversarial team games with low parameter k · 3-player Leduc/Liar's Dice | runtime: several orders of magnitude faster in games with low k | Helped |
| public observations instead of public states in the DAG construction (no inflation needed) | TB-DAG construction · theoretical construction family | TB-DAG size | Helped |
Closest papers by meaning
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.89)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (AAAI 2024 · similarity 0.89)
- The Complexity of Two-Team Polymatrix Games with Independent Adversaries (ICLR 2025 · similarity 0.88)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
- DAG-Based Column Generation for Adversarial Team Games (ICML 2024 · similarity 0.88)
- Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games (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.