arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0812.3465cs.LG
收藏

线性参数化Bandits

Linearly Parameterized Bandits

Cornell University(康奈尔大学);MIT(麻省理工学院)

Paat Rusmevichientong, John N. Tsitsiklis

摘要:

我们考虑强盗问题,涉及一个大的(可能是无限的)收集的武器,其中每个手臂的预期回报是一个线性函数的$r$ -维随机向量$\mathbf{Z} \in \mathbb{R}^r$,其中$r \geq 2$。目标是最小化累积后悔和贝叶斯风险。当一组武器对应的单位球,我们证明了遗憾和贝叶斯风险是为了$Θ(r \sqrt{T})$,通过建立一个任意的政策的下限,并显示匹配的上限是通过一个政策,探索和开发阶段之间的交替。基于相位的政策也被证明是有效的,如果一组武器满足一个强凸性条件。对于一般的武器集的情况下,我们描述了一个接近最优的政策,其遗憾和贝叶斯风险承认的形式$O(r \sqrt{T} \log^{3/2} T)$的上界。

英文摘要:

We consider bandit problems involving a large (possibly infinite) collection of arms, in which the expected reward of each arm is a linear function of an $r$-dimensional random vector $\mathbf{Z} \in \mathbb{R}^r$, where $r \geq 2$. The objective is to minimize the cumulative regret and Bayes risk. When the set of arms corresponds to the unit sphere, we prove that the regret and Bayes risk is of order $Θ(r \sqrt{T})$, by establishing a lower bound for an arbitrary policy, and showing that a matching upper bound is obtained through a policy that alternates between exploration and exploitation phases. The phase-based policy is also shown to be effective if the set of arms satisfies a strong convexity condition. For the case of a general set of arms, we describe a near-optimal policy whose regret and Bayes risk admit upper bounds of the form $O(r \sqrt{T} \log^{3/2} T)$.

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。

↑