Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies
混合现实数字孪生:利用物理与虚拟世界实现多智能体强化学习策略的混合仿真到现实过渡
机构 * Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR)(汽车工程系,克莱姆森大学国际汽车研究中心(CU-ICAR))
专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.LG
AI总结 本文提出混合现实数字孪生框架,通过并行化和域随机化技术,显著提升多智能体强化学习策略的训练效率和仿真到现实迁移性能。
Comments Accepted in IEEE Robotics and Automation Letters (RA-L) and additionally accepted to be presented at IEEE International Conference on Robotics and Automation (ICRA) 2026
Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 9, pp. 9040-9047, Sept. 2025