Research map / Optimization / Nonconvex and smooth optimization
State-Action Selection in General Stochastic Games under Regularized Policy Gradient Methods
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.
Studies regularized policy gradient methods in general-sum stochastic games and characterizes the long-run behavior of policy iterates using setwise solution concepts.
Problem
Learning pointwise solution concepts (e.g., Nash equilibria) in general-sum stochastic games is intractable, so the paper targets the long-run behavior of policy gradient iterates under less restrictive setwise solution concepts.
Approach
Shifts focus from pointwise to setwise solution concepts and analyzes the long-run behavior of a general class of regularized policy gradient methods in episodic general-sum stochastic games, describing which state-action sets the iterates concentrate on.
Closest papers by meaning
- Accelerated Regularized Learning in Finite N-Person Games (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 0.90)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.89)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.89)
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence (ICLR 2025 · similarity 0.89)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · 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.