ReWAM: Reciprocal World Action Models for Interactive Autonomous Driving
ReWAM introduces a game-theoretic framework to model reciprocal influence between an ego agent and other agents in autonomous driving. It replaces simultaneous coupling with a hierarchy of bounded strategic responses, allowing agents to be mutually responsive decision-makers grounded in a shared world model. This improves performance in dense interactions by capturing how each agent's action is shaped by the preceding strategies of others.