Research map / Learning theory and algorithms / Submodular and game algorithms
Double-Oracle Sampling Method for Stackelberg Equilibrium Approximation in General-Sum 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 O2UCT instead of MILP-based methods on larger WHG and WNZ instances | Stackelberg equilibrium approximation · WHG and WNZ, 10^7-node bucket | game instances solved within 200h: O2UCT solved all game instances; CBK2018(a) solved 23 WHG and 13 WNZ games | Helped |
| Use O2UCT instead of solver-based methods | Stackelberg equilibrium approximation · General game instances | maximum game nodes computed: 10^9 game nodes using 8GB; solver based methods started running out of 256GB for games with 10^7 nodes | Helped |
| Use O2UCT instead of MILP-based methods on small games | Stackelberg equilibrium approximation · WHG, WNZ, and SEG small instances | computation time | Hurt |
| Use O2UCT instead of MILP-based methods on larger games | Stackelberg equilibrium approximation · WHG, WNZ, and SEG large instances | computation time | Helped |
| Use O2UCT instead of CBK2018 variants | Stackelberg equilibrium approximation · WHG, WNZ, and SEG | Leader's payoff | Helped |
Closest papers by meaning
- Using Correlated Strategies for Computing Stackelberg Equilibria in Extensive-Form Games (AAAI 2016 · similarity 0.91)
- Safe Search for Stackelberg Equilibria in Extensive-Form Games (AAAI 2021 · similarity 0.90)
- Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games (AAAI 2023 · similarity 0.89)
- Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games (NeurIPS 2021 · similarity 0.88)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.87)
- Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games (ICML 2024 · 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.