Research map / Multi-agent systems and games / Games and equilibria
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum 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 a core set and weighted least squares instead of querying and estimating every action pair | Learning Stackelberg in linear bandit games · Linear bandit games | sample complexity: \wt{O}(d^2/\eps^2) queries; lower bound \Omega(d/\eps^2) | Helped |
| use reward-free RL exploration to estimate both rewards over the follower's near-optimal policy set | Learning Stackelberg in bandit-RL games · Bandit-RL games | episodes: \wt{O}(H^5S^2AB/\varepsilon^2+H^7S^4AB/\varepsilon) | Helped |
| use optimistic tie-breaking in simultaneous matrix games | Learning Stackelberg in simultaneous matrix games · Simultaneous matrix games | runtime: the same \wt{O}(AB/\varepsilon^2) sample complexity | Helped |
Closest papers by meaning
- When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? (ICLR 2022 · similarity 0.92)
- Sample-Efficient Multi-Agent RL: An Optimization Perspective (ICLR 2024 · similarity 0.90)
- Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis (NeurIPS 2025 · similarity 0.90)
- The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback (ICML 2025 · similarity 0.90)
- Impact of Decentralized Learning on Player Utilities in Stackelberg Games (ICML 2024 · similarity 0.90)
- Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions (NeurIPS 2026 · similarity 0.89)
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.