Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving

ArXi:2603.20230v1 Announce Type: cross Autonomous driving involves multiple, often conflicting objectives such as safety, efficiency, and comfort. In reinforcement learning (RL), these objectives are typically combined through weighted summation, which collapses their relative priorities and often yields policies that violate safety-critical constraints. To overcome this limitation, we