Research map / Learning theory and algorithms / Submodular and game algorithms
Solving Large Sequential Games with the Excessive Gap Technique
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 aggressive μ reduction with practical initial μ and μ balancing (ablation) | EGT · Endgame 7 | iterations to 1mbb: about 3000 -> about 400 | Helped |
| Use aggressive μ reduction with practical initial μ and μ balancing (ablation) | EGT · Endgame 2 | iterations to 1mbb: about 400 iterations for EGT/as; EGT is slowest | Mixed |
| Use EGT/as instead of CFR+ | River endgames · Endgame 2 and Endgame 7 | gradient computations to 1mbb: about 800 -> about 1800 | Hurt |
| Use practical EGT without aggressive μ reduction instead of CFR(RM) or CFR(RM$^+$) | Endgame 7 · Endgame 7 | iterations to 1mbb: about 3000 | No clear effect |
| Use EGT/as instead of CFR(RM$^+$) | River endgames · Endgame 2 and Endgame 7 | iterations to 1mbb: about 400 versus about 3000 in Endgame 7 | Helped |
Closest papers by meaning
- Sparsified Linear Programming for Zero-Sum Equilibrium Finding (ICML 2020 · similarity 0.91)
- Faster Game Solving via Hyperparameter Schedules (AAAI 2026 · similarity 0.90)
- Last-iterate Convergence in Extensive-Form Games (NeurIPS 2021 · similarity 0.90)
- Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play (NeurIPS 2024 · similarity 0.89)
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions (NeurIPS 2019 · similarity 0.89)
- Preference-CFR: Beyond Nash Equilibrium for Better Game Strategies (ICML 2025 · similarity 0.86)
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.