PSN Game: A Player Selection Network for Scalable Game-Theoretic Prediction and Planning
Abstract
While game-theoretic planning frameworks are effective at modeling multi-agent interactions, they require solving large optimization problems where the number of variables increases with the number of agents, resulting in long computation times that limit their use in large-scale, real-time systems. To address this issue, we propose PSN Game—a learning-based, game-theoretic prediction and planning framework that reduces game size by learning a Player Selection Network (PSN), together with a Goal Inference Network (GIN) for incomplete-information settings.
Type
Publication
Transactions on Machine Learning Research (TMLR)
