Area-wide traffic signal control based on a deep graph Q-Network (DGQN) trained in an asynchronous manner
This is an incremental improvement for traffic management systems, offering better control in large urban networks.
The paper tackled the problem of jointly controlling traffic signals in a large network by addressing issues like exponential action space, spatio-temporal dependencies, and slow training, resulting in a deep graph Q-network that outperformed other RL algorithms and fixed-signal operations in Seoul.
Reinforcement learning (RL) algorithms have been widely applied in traffic signal studies. There are, however, several problems in jointly controlling traffic lights for a large transportation network. First, the action space exponentially explodes as the number of intersections to be jointly controlled increases. Although a multi-agent RL algorithm has been used to solve the curse of dimensionality, this neither guaranteed a global optimum, nor could it break the ties between joint actions. The problem was circumvented by revising the output structure of a deep Q-network (DQN) within the framework of a single-agent RL algorithm. Second, when mapping traffic states into an action value, it is difficult to consider spatio-temporal correlations over a large transportation network. A deep graph Q-network (DGQN) was devised to efficiently accommodate spatio-temporal dependencies on a large scale. Finally, training a RL model to jointly control traffic lights in a large transportation network requires much time to converge. An asynchronous update methodology was devised for a DGQN to quickly reach an optimal policy. Using these three remedies, a DGQN succeeded in jointly controlling the traffic lights in a large transportation network in Seoul. This approach outperformed other state-of-the-art RL algorithms as well as an actual fixed-signal operation.