Research map / Reinforcement learning / MDPs and planning
Offline Learning in Markov Games with General Function Approximation
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 adaptive coverage–suboptimality trade-offs for deviation policies instead of requiring coverage of every unilateral deviation | BCEL for offline Markov games · Offline Markov games; two-player zero-sum matrix-game example | sample complexity: unilateral coverage: \otilde(\frac{1}{p_2 \epsilon^2}); adaptive bound: \otilde(\max\{\frac{1}{p_2}, \frac{1}{p_1\epsilo | Helped |
| Model state-value functions and use action importance weighting instead of modeling joint-action Q-functions | BCEL V-type variant · Tabular Markov games | dependence on number of agents | Helped |
Closest papers by meaning
- When are Offline Two-Player Zero-Sum Markov Games Solvable? (NeurIPS 2022 · similarity 0.93)
- Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games (ICML 2025 · similarity 0.91)
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games (ICML 2024 · similarity 0.91)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.90)
- Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics (NeurIPS 2026 · similarity 0.90)
- Offline-Online Reinforcement Learning for Linear Mixture MDPs (NeurIPS 2026 · similarity 0.90)
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.