Research map / Bandits and online learning / Online convex optimization and games
Regret-Minimizing Double Oracle for 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 |
|---|---|---|---|
| Use periodic best-response computation with periodicity 50 | PDO · Sequential Blotto | exploitability | Helped |
| Use periodic best-response computation with periodicity 50 | PDO · Large Kuhn Poker | exploitability | Helped |
| Use periodic rather than every-iteration best-response computation | PDO versus XODO · Leduc Poker | convergence speed | Helped |
| Set periodicity to 50 (ablation) | PDO · Leduc Poker Dummy | time to small exploitability | Helped |
| Use periodicity 50 (ablation) | PDO · Leduc Poker | exploitability | Helped |
| Use periodicity 100 (ablation) | PDO · Leduc Poker | exploitability | Helped |
| Increase periodicity (ablation) | PDO · Oshi Zumo | early-stage exploitability decrease | Hurt |
| Increase periodicity (ablation) | PDO · Oshi Zumo | later exploitability | Helped |
| Output the last-window average strategy instead of the overall average strategy (ablation) | PDO · Extensive-form games | convergence speed | Helped |
| Use PDO instead of XDO | Extensive-form double-oracle methods · Leduc Poker | exploitability | Helped |
| Use PDO instead of CFR+ | Extensive-form game solvers · Leduc Poker | later-stage exploitability | Helped |
| Use PDO instead of competing algorithms | Extensive-form game solvers · Leduc Poker Dummy | exploitability | Helped |
Closest papers by meaning
- Last-iterate Convergence in Extensive-Form Games (NeurIPS 2021 · similarity 0.91)
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions (NeurIPS 2019 · similarity 0.91)
- Extensive-Form Game Solving via Blackwell Approachability on Treeplexes (NeurIPS 2024 · similarity 0.87)
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games (ICLR 2025 · similarity 0.87)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (AAAI 2024 · similarity 0.87)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · 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.