Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving
基于混合动作的多目标兼容自动驾驶强化学习
机构 * College of Automotive and Energy Engineering, Tongji University(同济大学汽车与能源工程学院) ; Department of Data and Systems Engineering, University of Hong Kong(香港大学数据与系统工程系)
AI总结 本文提出一种多目标集成-批评强化学习方法,通过混合参数化动作空间结构和不确定性探索机制,提升自动驾驶在多目标兼容性、效率和安全性方面的性能。
Comments 14 pages, accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)