Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
动态渐进式参数高效专家库混合用于终身机器人学习
机构 * The University of Hong Kong(香港大学) ; Institute of Artificial Intelligence (TeleAI), China Telecom(人工智能研究院(TeleAI),中国电信) ; Huawei Cloud Computing Technologies(华为云计算技术) ; Ola Dimensions ; HKU Shanghai Intelligent Computing Research Center(香港大学上海智能计算研究中心)
专题命中 Agent评测 :agent(abstract);分类 cs.LG
AI总结 针对终身学习中任务标识不可用和知识隔离问题,提出动态渐进式参数高效专家库混合(DMPEL),通过构建低秩专家库和轻量路由器实现灵活的前向迁移,并引入专家系数回放缓解遗忘,在LIBERO基准上以最少可训练参数和存储超越现有方法。
Comments Accepted to Transactions on Machine Learning Research (TMLR) at https://openreview.net/forum?id=MHVBrjS8cG . Code is available at https://github.com/HarryLui98/DMPEL