The Irrevocable Multiarmed Bandit Problem
研究了在同时拉动多个臂且不允许重新使用已丢弃臂的约束下，多臂老虎机问题的性能损失，并提出了性能优异的“打包”启发式算法。
This paper considers the multiarmed bandit problem with multiple simultaneous arm pulls and the additional restriction that we do not allow recourse to arms that were pulled at some point in the past but then discarded. This additional restriction is highly desirable from an operational perspective, and we refer to this problem as the “irrevocable multiarmed bandit” problem. We observe that natural modifications to well-known heuristics for multiarmed bandit problems that satisfy this irrevocability constraint have unsatisfactory performance and, thus motivated, introduce a new heuristic: the “packing” heuristic. We establish through numerical experiments that the packing heuristic offers excellent performance, even relative to heuristics that are not constrained to be irrevocable. We also provide a theoretical analysis that studies the “price” of irrevocability, i.e., the performance loss incurred in imposing the constraint we propose on the multiarmed bandit model. We show that this performance loss is uniformly bounded for a general class of multiarmed bandit problems and indicate its dependence on various problem parameters. Finally, we obtain a computationally fast algorithm to implement the packing heuristic; the algorithm renders the packing heuristic computationally cheaper than methods that rely on the computation of Gittins indices.