Online machine learning (OML) algorithms do not need any training and can be deployed directly in an unknown environment. OML includes multi-armed bandit (MAB) algorithms that can identify the best arm among several arms via exploration (select all arms sufficient number of times) and exploitation (select best arm as many times as possible) trade-off. In this paper, we efficiently map the MAB algorithms on Zynq System on Chip (ZSoC) and make it reconfigurable such that the number of arms, as well as type of algorithm, can be changed on-the-fly.