In this paper we examine the effectiveness of several multi-arm bandit algorithms when used as a trust system to select agents to delegate tasks to. In contrast to existing work, we allow for recursive delegation to occur. That is, a task delegated to one agent can be delegated onwards by that agent, with further delegation possible until some agent finally executes the task. We show that modifications to the standard multi-arm bandit algorithms can provide improvements in performance in such recursive delegation settings.

翻译：本文研究了多种多臂老虎机算法在作为信任系统选择委派任务代理时的有效性。与现有工作不同，我们允许发生递归委派，即委派给一个代理的任务可由该代理继续向下委派，且可进行进一步委派，直至某个代理最终执行该任务。我们表明，对标准多臂老虎机算法进行修改可在此类递归委派场景中提升性能。