Learning to Orchestrate Agents under Uncertainty
学习在不确定性下编排智能体
机构 * Department of Applied Mathematics and Theoretical Physics, University of Cambridge(应用数学与理论物理系,剑桥大学) ; Centre for Human-Inspired Artificial Intelligence, University of Cambridge(启发式人工智能中心,剑桥大学) ; African Institute for Mathematical Sciences, South Africa(南非数学科学研究所) ; Department of Engineering Science, University of Oxford(工程科学系,牛津大学)
AI总结 提出BOT-Orch框架,将编排问题转化为带正则化的多臂赌博机问题,在不确定性下实现异构智能体的自适应编排,理论保证遗憾界为O(√T)并优于基线。