Reinforcement Learning based Intelligent Traffic Signal Control using n-step SARSA

In this paper, we propose a reinforcement learning based traffic signal controller. We use the n-step SARSA algorithm to design a predictive approach to traffic signal control. An optimal policy that effectively minimizes the probability of congestion in the network is arrived at in this paper. Our results show that our algorithm outperforms conventional approaches such as the longest queue first technique. The overall approach is so designed as to make it implementable in low-cost real-time systems.