Research map / Learning theory and algorithms / Submodular and game algorithms
\(\varepsilon\)-Optimally Solving Two-Player Zero-Sum POSGs
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.
Proposes a framework for ε-optimally solving two-player zero-sum POSGs via a lossless reduction connecting them to dynamic programming for zero-sum stochastic games.
Problem
Solving two-player zero-sum partially observable stochastic games (zs-POSGs) to ε-optimality, which lacks a principled, lossless connection to dynamic programming methods used for zero-sum stochastic games.
Approach
Establishes a lossless reduction from zs-POSGs to zero-sum stochastic games so that DP techniques for zs-SGs can be transferred, addressing the gap left by prior lossy attempts.
Closest papers by meaning
- Solving Partially Observable Stochastic Games with Public Observations (AAAI 2019 · similarity 0.91)
- Scalable Solutions to Zero-Sum Partially Observable Stochastic Games Through Belief Aggregation with Approximation Guarantees (AAAI 2026 · similarity 0.89)
- Solving Zero-Sum Convex Markov Games (ICML 2025 · similarity 0.88)
- Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis (NeurIPS 2024 · similarity 0.87)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.87)
- Approximate State Abstraction for Markov Games (AAAI 2025 · similarity 0.87)
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.