Modular Discovery of General Game-Playing Algorithms with Large Language Models
General Game Playing across arbitrary games from rules alone remains challenging due to differing algorithmic requirements across game classes and strict decision-time constraints. Rather than hand-designing search heuristics for specific domains, can we leverage Large Language Models (LLMs) to discover general game-pl...
Zun Li, John Schultz, Marc Lanctot et al.
· 0 citations