GPDS: A multi-agent deep reinforcement learning game for anti-jamming secure computing in MEC network

作者：

Highlights：

• We first model the MEC anti-jammer as a multi-user continuous game.

• A post decision state is proposed to deal with dynamic unknown information.

• A minimax gradient strategy is proposed to realize learning generalization.

• State-of-the-art methods are outperformed in both parameters and performance.

摘要

•We first model the MEC anti-jammer as a multi-user continuous game.•A post decision state is proposed to deal with dynamic unknown information.•A minimax gradient strategy is proposed to realize learning generalization.•State-of-the-art methods are outperformed in both parameters and performance.

论文关键词：Deep reinforcement learning,Multi-agent,Secure computing,Decision-making,Mobile Edge Computing (MEC)

论文评审过程：Received 12 April 2022, Revised 26 July 2022, Accepted 2 August 2022, Available online 10 August 2022, Version of Record 17 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118394