arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1011.4752math.OCcs.LGcs.NImath.PR
收藏

非贝叶斯不安多臂强盗:一个近对数后悔的案例

The Non-Bayesian Restless Multi-Armed Bandit: a Case of Near-Logarithmic Regret

University of Southern California(南加州大学)

Wenhan Dai, Yi Gai, Bhaskar Krishnamachari, Qing Zhao

摘要:

在经典的贝叶斯不安分多臂强盗(RMAB)问题中,存在$N$臂,每个臂上的奖励在每个时刻以参数已知的马尔可夫链形式演化.玩家寻求在每次激活$K \geq 1$臂,以便最大化在多次游戏中获得的预期总奖励。RMAB是一个具有挑战性的问题,通常被认为是PSPACE困难的。在这项工作中,我们认为更难的非贝叶斯RMAB,其中的马尔可夫链的参数被假定为未知的\emph{a priori}。我们开发了一个原始的方法来解决这个问题,适用于当相应的贝叶斯问题的结构,根据已知的参数值,最优解是一个规定的有限集的政策。在这样的设置中,我们建议学习的最佳政策,非贝叶斯RMAB采用一个合适的元政策,把每个政策从这个有限集作为一个手臂在一个不同的非贝叶斯多臂强盗问题的单臂选择政策是最佳的。我们证明了这种方法,通过开发一种新的感知策略,在未知的动态信道上的机会频谱接入。我们证明了我们的策略实现了接近对数的遗憾(与模型感知的精灵相比,预期奖励的差异),这导致了在已知模型下最优策略可以实现的相同平均奖励。这是第一个这样的结果在文献中的非贝叶斯RMAB。

英文摘要:

In the classic Bayesian restless multi-armed bandit (RMAB) problem, there are $N$ arms, with rewards on all arms evolving at each time as Markov chains with known parameters. A player seeks to activate $K \geq 1$ arms at each time in order to maximize the expected total reward obtained over multiple plays. RMAB is a challenging problem that is known to be PSPACE-hard in general. We consider in this work the even harder non-Bayesian RMAB, in which the parameters of the Markov chain are assumed to be unknown \emph{a priori}. We develop an original approach to this problem that is applicable when the corresponding Bayesian problem has the structure that, depending on the known parameter values, the optimal solution is one of a prescribed finite set of policies. In such settings, we propose to learn the optimal policy for the non-Bayesian RMAB by employing a suitable meta-policy which treats each policy from this finite set as an arm in a different non-Bayesian multi-armed bandit problem for which a single-arm selection policy is optimal. We demonstrate this approach by developing a novel sensing policy for opportunistic spectrum access over unknown dynamic channels. We prove that our policy achieves near-logarithmic regret (the difference in expected reward compared to a model-aware genie), which leads to the same average reward that can be achieved by the optimal policy under a known model. This is the first such result in the literature for a non-Bayesian RMAB.

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。

↑