Research map / Multi-agent systems and games / Games and equilibria
Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proves that policy gradient methods converge globally to Nash equilibria in imperfect-information extensive-form games despite nonconvexity.
Problem
Little is known about provable equilibrium convergence for MARL algorithms applied to imperfect-information extensive-form games, due to inherent nonconvexity of the policy optimization problem.
Approach
Provides a global convergence guarantee for policy gradient methods in extensive-form games, addressing the nonconvexity that prior analyses could not handle; the abstract is truncated so the specific technique is not stated.
Closest papers by meaning
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.94)
- Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence (ICML 2022 · similarity 0.92)
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property (AAAI 2024 · similarity 0.91)
- Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback (ICML 2025 · similarity 0.91)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.90)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · 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.