With the rapid development of Chinese economy and automotive industry, urban traffic congestion has become increasingly serious. Therefore, how to effectively alleviate the traffic congestion and improve the efficiency of vehicles has become the main concern. Traffic signal control is one of the effective ways to solve urban traffic congestion. In this paper, a traffic signal control method based on Action-Dependent Heuristic Dynamic Programming (ADHDP) is investigated. The control algorithm is simulated on two intersections, both of which have two phases with four entrance approaches. The computer simulation results show that the control method has the better ability of on-line learning compared with traditional Fix-Time Control, and can effectively improve the average speed of vehicles, and reduce travel time and alleviate the traffic pressure.