Research map / Learning theory and algorithms / Submodular and game algorithms
Solving Large Extensive-Form Games with Strategy Constraints
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 Constrained CFR instead of solving the constrained game with an LP | Transit game · Transit game, w=8 | risk-bound deviation: within 0.001 | Helped |
| Use Constrained CFR instead of solving the constrained game with an LP | Transit game · Transit game, w=8 | exploitability difference from LP: within 0.001 | No clear effect |
| Use Constrained CFR rather than the LP solver | Transit game · Transit game, w=10 | computation time: more than an order of magnitude | Helped |
| Infer opponent strategies from partial observations using sequence-form constraints | Constrained CFR opponent modeling · Leduc Hold'em | expected value against target profile | Helped |
| Use looser confidence intervals (higher confidence γ) | Constrained CFR opponent modeling · Leduc Hold'em | expected value against target profile: fewer than 100 observed games on average; fewer than 200 observed games consistently | Helped |
| Use lower confidence levels (tighter constraints) | Constrained CFR opponent modeling · Leduc Hold'em | expected value against target profile | Mixed |
| Increase the number of observed games used to construct constraints | Constrained CFR opponent modeling · Leduc Hold'em | expected value against target profile | Helped |
Closest papers by meaning
- Regret Minimization in Behaviorally-Constrained Zero-Sum Games (ICML 2017 · similarity 0.91)
- Counterfactual Regret Minimization in Sequential Security Games (AAAI 2016 · similarity 0.90)
- Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium (NeurIPS 2019 · similarity 0.90)
- Solving Imperfect-Recall Games via Sum-of-Squares Optimization (ICML 2026 · similarity 0.89)
- Computing Team-Maxmin Equilibria in Zero-Sum Multiplayer Extensive-Form Games (AAAI 2020 · similarity 0.89)
- Sparsified Linear Programming for Zero-Sum Equilibrium Finding (ICML 2020 · similarity 0.89)
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.