Research map / Optimization / Nonconvex and smooth optimization
On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games
Runyu Zhang, Jincheng Mei, Bo Dai, Dale Schuurmans, Na Li
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 |
|---|---|---|---|
| add log-barrier regularization to softmax gradient play | Gradient play · bad initialization near non-NE stationary point | convergence to Nash equilibrium | Improved |
| add log-barrier regularization to softmax natural gradient play | Natural gradient play · two-player identical-reward matrix game | escape from non-NE stationary regions | Improved |
| use natural gradient play instead of gradient play | Softmax policy parameterization · two-player identical-reward matrix game | convergence speed | Improved |
| add log-barrier regularization to natural gradient play | Natural gradient play · two-player identical-reward matrix game | numerical stability | Hurt |
| start from uniform initialization without regularization | Gradient play and natural gradient play · two-player identical-reward matrix game | NE gap | Hurt |
| add log-barrier regularization | Softmax gradient play · iteration complexity bound | dependence on action set size | Hurt |
Closest papers by meaning
- Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence (ICML 2022 · similarity 0.93)
- Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games (ICLR 2022 · similarity 0.92)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.92)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.91)
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.89)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (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.
