انجمن کامپیوتر ایران

The single traffic signal control agent improves its control ability with the NNQ-learning method. This paper proposes a Neural_Network_Q_learning (NNQL) approach with fuzzy reward designed for online learning of traffic lights behaviors .The Q-function table becomes too large for the required state/action resolution. In these cases, tabular Q-learning needs a very long learning time and memory requirements which makes the implementation of the algorithm in real-time control architecture impractical. To solve the problem of coordination between three TSCAs (Traffic Signal Control Agents) we used game theory. To test the efficiency of the coordination mechanism, a prototype traffic simulator was programmed in visual C++. Results using cooperative traffic agents are compared to results of control simulations where noncooperative agents were deployed. The result indicates that the new coordination method proposed in this paper is effective.