TSC: Topology-Conditioned Stackelberg Coordination for Multi-Agent Reinforcement Learning in Interactive Driving
TSC:基于拓扑条件的Stackelberg协调用于交互驾驶中的多智能体强化学习
机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,自动化研究所) ; School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) ; Department of Natural Sciences, University of Durham(达勒姆大学自然科学系) ; College of Civil and Transportation Engineering, Shenzhen University(深圳大学土木与交通工程学院) ; Chair of Robotics, Artificial Intelligence and Realtime Systems, Technical University of Munich(慕尼黑技术大学机器人、人工智能与实时系统教授职位)
专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract)
AI总结 TSC通过拓扑条件的Stackelberg协调方法,在无通信执行下实现密集交通中的去中心化多智能体强化学习,提升训练稳定性和安全性。
Comments 12 pages, 8 figures