Research map / Learning theory and algorithms / Submodular and game algorithms
Complexity and Algorithms for Exploiting Quantal Opponents in Large Two-Player 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 restricted quantal response (RQR) instead of CFR-QR | CFR-based strategy computation · Goofspiel 7 | gain: 2.357 -> 2.412 | Helped |
| Use restricted quantal response (RQR) instead of CFR-QR | CFR-based strategy computation · Goofspiel 7 | exploitability: 4.045 -> 3.849 | Helped |
| Use RQR instead of Nash strategies | zero-sum NFGs and EFGs · Zero-sum games | gain | Helped |
| Use RQR instead of QNE | zero-sum NFGs and EFGs · Zero-sum games | exploitability | Helped |
| Use RQR instead of QNE | general-sum NFGs · General-sum games | expected utility against BR | Helped |
| Use RQR instead of GA | strategy computation · Large games | scalability | Helped |
| Use RQR instead of QNE as rationality λ increases | logit quantal-response opponents · Games with varying rationality | exploitability | Helped |
| Use RQR instead of QNE | CFR-based strategy computation · Leduc Hold'em | exploitability | Helped |
| Use regret minimization instead of gradient ascent | QSE approximation · Normal-form and extensive-form games | scalability | Helped |
| Use QSE gradient ascent instead of scalable regret-minimization heuristics | strategy computation · Zero-sum and general-sum games | gain | Helped |
| Vary the RQR mixture parameter p (ablation) | CFR-based strategy computation · Leduc Hold'em | expected utility against CLQR | Mixed |
| Use RQR instead of CFR | CFR-based strategy computation · Goofspiel 7 | gain: 1.191 -> 2.412 | Helped |
Closest papers by meaning
- Computing Quantal Stackelberg Equilibrium in Extensive-Form Games (AAAI 2021 · similarity 0.91)
- Exploiting Opponents Under Utility Constraints in Sequential Games (NeurIPS 2021 · similarity 0.88)
- Perturbing Best Responses in Zero-Sum Games (AAAI 2026 · similarity 0.88)
- Learning Markov Games with Adversarial Opponents: Efficient Algorithms and Fundamental Limits (ICML 2022 · similarity 0.87)
- Advantage Alignment Algorithms (ICLR 2025 · similarity 0.86)
- Commitment to Sparse Strategies in Two-Player Games (AAAI 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.