arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1311.2889cs.LGcs.SIstat.ML
收藏

矩阵计算的强化学习:以PageRank为例

Reinforcement Learning for Matrix Computations: PageRank as an Example

Indian Institute of Technology(印度理工学院)

Vivek S. Borkar, Adwaitvedant S. Mathkar

摘要:

强化学习作为一种用于模拟驱动的近似动态规划的技术已经得到了广泛的普及。一个鲜为人知的方面是,使它在动态规划中有效的原因也可以被利用来将其用于涉及非负矩阵的某些矩阵计算的分布式方案。本着这种精神,我们提出了一个强化学习算法的PageRank计算后,类似的计划近似动态规划。该算法具有易于分布式实现的优点,更重要的是,是无模型的,即,不依赖于关于随机网络冲浪者模型中的转移概率的任何特定假设。我们分析了它的收敛性和有限时间行为,并给出了一些支持的数值实验。

英文摘要:

Reinforcement learning has gained wide popularity as a technique for simulation-driven approximate dynamic programming. A less known aspect is that the very reasons that make it effective in dynamic programming can also be leveraged for using it for distributed schemes for certain matrix computations involving non-negative matrices. In this spirit, we propose a reinforcement learning algorithm for PageRank computation that is fashioned after analogous schemes for approximate dynamic programming. The algorithm has the advantage of ease of distributed implementation and more importantly, of being model-free, i.e., not dependent on any specific assumptions about the transition probabilities in the random web-surfer model. We analyze its convergence and finite time behavior and present some supporting numerical experiments.

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。

↑