Research map / Multi-agent systems and games / Games and equilibria
Provably Efficient Offline Multi-agent Reinforcement Learning via Strategy-wise Bonus
Qiwen Cui, Simon Shaolei Du
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Replace point-wise concentration with strategy-wise concentration | Offline two-player zero-sum Markov games · Offline two-player zero-sum Markov games | action-size dependence of sample complexity: AB -> (A+B) | Improved |
| Use strategy-wise bonus in place of point-wise bonus | Offline multi-player general-sum Markov games · Offline multi-player general-sum Markov games | action-size dependence of sample complexity: \sum_{j=1}^mA_j -> \Pi_{i=1}^m A_i | Improved |
| Use a pre-specified strategy class containing the target strategy | SBMM and SBSM · Offline Markov games | strategy-class complexity dependence: \sum_{j\in[m]}A_j -> \log(\mathcal{N}(\Pi)) | Improved |
Closest papers by meaning
- Sample-Efficient Tabular Self-Play for Offline Robust Reinforcement Learning (NeurIPS 2025 · similarity 0.91)
- Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization (AAAI 2025 · similarity 0.90)
- Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games (ICML 2025 · similarity 0.90)
- Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games (ICML 2024 · similarity 0.89)
- Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL (NeurIPS 2025 · similarity 0.88)
- Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty (ICML 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.
