Due to low complexity, power and bandwidth saving Distance Vector Routing has been introduced as one of the most popular dynamic routing protocol. However, this protocol has a serious drawback in practice called Count To Infinity problem or slow convergence. There are many proposed solutions in the literature to solve the problem, but all of these methods depend on the network topology, and impose much computational complexity to the network. In this paper, we introduce a new approach to solve the Count To Infinity using hidden markov model (HMM), which is one of the most important machine learning tools. As the modelling results show, the proposed method is completely independent from the network topology and simple with low computational complexity.