AI RESEARCH
Generative Evolutionary Meta-Solver (GEMS): Scalable Surrogate-Free Multi-Agent Reinforcement Learning
arXiv CS.LG
•
ArXi:2509.23462v2 Announce Type: replace Scalable multi-agent reinforcement learning (MARL) remains a central challenge for AI. Existing population-based methods, like Policy-Space Response Oracles, PSRO, require storing explicit policy populations and constructing full payoff matrices, incurring quadratic computation and linear memory costs. We present Generative Evolutionary Meta-Solver (GEMS), a surrogate-free framework that replaces explicit populations with a compact set of latent anchors and a single amortized generator.