SOURCE-LINKED INTELLIGENCE

NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space M

Read original source ↗ Open in workspace

recordType

paper

region

Global