Research map / Learning theory and algorithms / Submodular and game algorithms
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information 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 EPF function approximation to compute SEFCE | Stackelberg games · Resource Collection (J=7, n=4) | leader payoff | Helped |
| Use EPF function approximation instead of subgame-perfect Nash | Stackelberg games · Tantrum (n=25) | leader payoff | Helped |
| Use EPF function approximation instead of a non-strategic leader commitment | Stackelberg games · Resource Collection+ (J=9, n=6) | leader payoff | Helped |
| Learn EPFs from state and payoff features across varying game parameters | Featurized Tantrum · Tantrum with varying q parameters | payoff ratio κ | Helped |
| Increase game horizon n | EPF function approximation · Featurized Tantrum | payoff ratio κ | Hurt |
| Test on out-of-distribution q values | EPF function approximation · Featurized Tantrum | payoff ratio κ | Mixed |
Closest papers by meaning
- Using Correlated Strategies for Computing Stackelberg Equilibria in Extensive-Form Games (AAAI 2016 · similarity 0.90)
- Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games (NeurIPS 2023 · similarity 0.90)
- Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games (NeurIPS 2021 · similarity 0.90)
- Double-Oracle Sampling Method for Stackelberg Equilibrium Approximation in General-Sum Extensive-Form Games (AAAI 2020 · similarity 0.89)
- On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games (NeurIPS 2024 · similarity 0.88)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · 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.