Research map / Learning theory and algorithms / Submodular and game algorithms
Double Oracle Algorithm for Computing Equilibria in Continuous 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 double oracle algorithm instead of fictitious play | continuous polynomial game G1 · G1 | convergence speed | Helped |
| use the double oracle algorithm instead of fictitious play | continuous game G2 (Townsend function) · G2 | convergence speed | Helped |
| use the double oracle algorithm instead of fictitious play | continuous Colonel Blotto game · Colonel Blotto | convergence speed | Helped |
| initialize both players' strategy sets with the battlefield corner points instead of a random point (ablation) | double oracle for Colonel Blotto · Colonel Blotto, 3 battlefields, equal weights | convergence speed | Helped |
| initialize both players' strategy sets with the whole grid (ablation) | double oracle for Colonel Blotto · Colonel Blotto, 3 battlefields | iterations to convergence | Helped |
| use a random initial strategy instead of grid-aligned initial strategies (ablation) | double oracle for Colonel Blotto · Colonel Blotto, 3 battlefields | convergence speed | Hurt |
| vary the battlefield count while holding c fixed (ablation) | double oracle for Colonel Blotto · Colonel Blotto, 3 and 10 battlefields, c=1/16 | convergence speed | No clear effect |
| vary c (ablation) | double oracle for Colonel Blotto · Colonel Blotto | convergence speed | Mixed |
Closest papers by meaning
- Incremental Multiple Oracle (NeurIPS 2026 · similarity 0.92)
- Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along (NeurIPS 2026 · similarity 0.90)
- Regret-Minimizing Double Oracle for Extensive-Form Games (ICML 2023 · similarity 0.90)
- From Duels to Battlefields: Computing Equilibria of Blotto and Other Games (AAAI 2016 · similarity 0.89)
- Perturbing Best Responses in Zero-Sum Games (AAAI 2026 · similarity 0.89)
- Can Reinforcement Learning Solve Asymmetric Combinatorial-Continuous Zero-Sum Games? (ICLR 2025 · similarity 0.88)
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.