RLAR:一种基于增强学习的自适应路由算法

Reinforcement learning means learning a policy that a mapping of states into actions which based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. An adaptive routing algorithm which called RLAR is proposed, and the algorithm is based on reinforcement learning which implemented by gradient ascent algorithm. The performance of this algorithm and other routing methods is comprehensively compared and simulation results show that RLAR can remarkably enhance the performance of network routing.