Research map / Optimization / Nonconvex and smooth optimization
Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov 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 |
|---|---|---|---|
| Add entropy regularization with a geometrically decaying weight and inner-loop GDA | GDA for two-player zero-sum Markov games · Two-player zero-sum Markov games | gradient updates to an ε-approximate Nash equilibrium: O(ε^{-3}) | Helped |
| Add online polynomial decay of the entropy regularization weight | GDA for two-player zero-sum Markov games · Two-player zero-sum Markov games | last-iterate convergence rate: O(k^{-1/3}) | Helped |
| Add a fixed positive entropy regularization weight | GDA for entropy-regularized Markov games · Entropy-regularized two-player zero-sum Markov games | convergence to the regularized Nash equilibrium: linear convergence | Helped |
| Use diminishing entropy regularization instead of unregularized GDA | GDA for a completely mixed synthetic Markov game · Synthetic completely mixed Markov game | last-iterate convergence | Helped |
| Use unregularized GDA instead of diminishing-regularization GDA | GDA for a deterministic synthetic Markov game · Synthetic deterministic Markov game | convergence to the Nash equilibrium | No clear effect |
Closest papers by meaning
- Competitive Gradient Descent (NeurIPS 2019 · similarity 0.92)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.92)
- On the $O(1/T)$ Convergence of Alternating Gradient Descent–Ascent in Bilinear Games (ICLR 2026 · similarity 0.92)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.90)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.89)
- Accelerated Regularized Learning in Finite N-Person Games (NeurIPS 2024 · 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.