Credit and quality intelligent learning based multi-armed bandit scheme for unknown worker selection in multimedia MCS

Jianheng Tang, Feijiang Han, Kejia Fan, Wenxuan Xie, Pengzhi Yin, Zhenzhe Qu, Anfeng Liu, Neal N. Xiong, Shaobo Zhang, Tian Wang

Abstract: Highlights•A Credit and Quality Learning based Multi-armed Bandit (CQL-MAB) mechanism is proposed for multimedia data collection.•The CQL-MAB mechanism is the first to consider both workers’ credit and quality for post unknown worker selection.•A novel 2-level reward UCB index for MAB scheme are designed for the balance of exploration and exploitation.•The CQL-MAB is proved to achieve truthfulness, individual rationality and computational efficiency.•Experimental results show the state-of-art performance of CQL-MAB on revenue and regret.