arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1012.3005math.OCcs.LGcs.NIcs.SYeess.SYmath.PR
收藏

关于马尔可夫奖励的组合多臂老虎机问题

On the Combinatorial Multi-Armed Bandit Problem with Markovian Rewards

Ming Hsieh Department of Electrical Engineering University of Southern California(明斯海德电气工程系 美国南加州大学)

Yi Gai, Bhaskar Krishnamachari, Mingyan Liu

AI总结:

针对用户-资源匹配中状态演化为马尔可夫链的组合多臂老虎机问题,提出一种多项式存储和每步多项式复杂度的学习算法,实现接近对数时间的遗憾界。

摘要:

我们考虑经典多臂老虎机问题的一个组合推广,定义如下:给定一个二分图,包含 $M$ 个用户和 $N \geq M$ 个资源。对于每个用户-资源对 $(i,j)$,存在一个关联状态,该状态演化为一个参数未知的不可约非周期有限状态马尔可夫链,每次特定用户 $i$ 被分配资源 $j$ 时状态发生转移。用户 $i$ 每次被分配资源 $j$ 时获得一个依赖于对应状态的奖励。系统目标是学习用户与资源的最佳匹配,使得所有用户获得的长期奖励总和最大化。这对应于最小化遗憾,这里定义为最佳可能静态匹配所能获得的期望总奖励与给定算法所能达到的期望总奖励之间的差距。我们针对该问题提出了一种多项式存储和每步多项式复杂度的匹配学习算法。我们证明该算法能够实现均匀任意接近对数时间的遗憾,且遗憾与用户和资源数量成多项式关系。该公式广泛适用于网络中的调度和交换问题,并显著扩展了该领域的先前结果。

英文摘要:

We consider a combinatorial generalization of the classical multi-armed bandit problem that is defined as follows. There is a given bipartite graph of $M$ users and $N \geq M$ resources. For each user-resource pair $(i,j)$, there is an associated state that evolves as an aperiodic irreducible finite-state Markov chain with unknown parameters, with transitions occurring each time the particular user $i$ is allocated resource $j$. The user $i$ receives a reward that depends on the corresponding state each time it is allocated the resource $j$. The system objective is to learn the best matching of users to resources so that the long-term sum of the rewards received by all users is maximized. This corresponds to minimizing regret, defined here as the gap between the expected total reward that can be obtained by the best-possible static matching and the expected total reward that can be achieved by a given algorithm. We present a polynomial-storage and polynomial-complexity-per-step matching-learning algorithm for this problem. We show that this algorithm can achieve a regret that is uniformly arbitrarily close to logarithmic in time and polynomial in the number of users and resources. This formulation is broadly applicable to scheduling and switching problems in networks and significantly extends prior results in the area.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑