arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.09419cs.LGcs.AIstat.ML
收藏

图上的多臂Bandit学习

Multi-armed Bandit Learning on a Graph

Harvard School of Engineering and Applied Sciences(哈佛大学工程与应用科学学院);Stanford University(斯坦福大学);KTH(瑞典皇家理工学院)

Tianpeng Zhang, Kasper Johansson, Na Li

摘要:

多臂强盗(MAB)问题是一个简单而强大的框架,已被广泛研究的背景下的不确定性决策。在许多现实世界的应用中,例如机器人应用,选择手臂对应于约束下一个可用手臂(动作)的选择的物理动作。出于这一动机,我们研究了MAB的一个扩展,称为图强盗,其中代理在图上旅行,以最大限度地提高从不同节点收集的奖励。该图定义了代理在每一步选择下一个可用节点的自由度。我们假设图结构是完全可用的,但奖励分布是未知的。基于离线的基于图的规划算法和乐观原则,我们设计了一个学习算法,G-UCB,使用乐观原则平衡长期的探索和开发。我们表明,我们提出的算法实现了$O(\sqrt{|S|T\log(T)}+D|S|\log T)$学习遗憾,其中$|S|$是节点的数量和$D$是直径的图形,它匹配的理论下限$Ω(\sqrt{|S|T})$的对数因子。据我们所知,这一结果是第一个紧遗憾界在非情节,非折扣学习问题与已知的确定性过渡。数值实验证实,我们的算法优于几个基准。

英文摘要:

The multi-armed bandit(MAB) problem is a simple yet powerful framework that has been extensively studied in the context of decision-making under uncertainty. In many real-world applications, such as robotic applications, selecting an arm corresponds to a physical action that constrains the choices of the next available arms (actions). Motivated by this, we study an extension of MAB called the graph bandit, where an agent travels over a graph to maximize the reward collected from different nodes. The graph defines the agent's freedom in selecting the next available nodes at each step. We assume the graph structure is fully available, but the reward distributions are unknown. Built upon an offline graph-based planning algorithm and the principle of optimism, we design a learning algorithm, G-UCB, that balances long-term exploration-exploitation using the principle of optimism. We show that our proposed algorithm achieves $O(\sqrt{|S|T\log(T)}+D|S|\log T)$ learning regret, where $|S|$ is the number of nodes and $D$ is the diameter of the graph, which matches the theoretical lower bound $Ω(\sqrt{|S|T})$ up to logarithmic factors. To our knowledge, this result is among the first tight regret bounds in non-episodic, un-discounted learning problems with known deterministic transitions. Numerical experiments confirm that our algorithm outperforms several benchmarks.

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。

↑