期刊名称：International Journal of Distributed Sensor Networks
印刷版ISSN：1550-1329
电子版ISSN：1550-1477
出版年度：2021
卷号：17
期号：12
页码：1-12
DOI：10.1177/15501477211059934
语种：English
出版社：Hindawi Publishing Corporation
摘要：Policy gradient methods are effective means to solve the problems of mobile multimedia data transmission in Content Centric Networks. Current policy gradient algorithms impose high computational cost in processing high-dimensional data. Meanwhile, the issue of privacy disclosure has not been taken into account. However, privacy protection is important in data training. Therefore, we propose a randomized block policy gradient algorithm with differential privacy. In order to reduce computational complexity when processing high-dimensional data, we randomly select a block coordinate to update the gradients at each round. To solve the privacy protection problem, we add a differential privacy protection mechanism to the algorithm, and we prove that it preserves the ε-privacy level. We conduct extensive simulations in four environments, which are CartPole, Walker, HalfCheetah, and Hopper. Compared with the methods such as important-sampling momentum-based policy gradient, Hessian-Aided momentum-based policy gradient, REINFORCE, the experimental results of our algorithm show a faster convergence rate than others in the same environment.
