Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving
超越标量奖励:用于安全可靠自动驾驶的预序目标分布强化学习
机构 * FZI Research Center for Information Technology(弗劳恩霍夫研究所信息技术研究中心) ; Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)
专题命中 仿真评测 :autonomous driving(title,abstract);分类 cs.RO、cs.AI
AI总结 本文提出预序多目标MDP框架,通过引入量化主导指标提升自动驾驶安全性和可靠性,实验表明其在Carla中表现出更优的性能和更稳健的策略。
Comments First and Second authors contributed equally; Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA 2026)