Deep Reinforcement Learning for Traffic Light Control in Vehicular Networks

3 code implementations • 29 Mar 2018 • Xiaoyuan Liang, Xunsheng Du, Guiling Wang, Zhu Han

In terms of how to dynamically adjust traffic signals' duration, existing works either split the traffic signal into equal duration or extract limited traffic information from the real data.

Q-Learning reinforcement-learning +1

A Deep Spatio-Temporal Fuzzy Neural Network for Passenger Demand Prediction

no code implementations • 13 May 2019 • Xiaoyuan Liang, Guiling Wang, Martin Renqiang Min, Yi Qi, Zhu Han

In spite of its importance, passenger demand prediction is a highly challenging problem, because the demand is simultaneously influenced by the complex interactions among many spatial and temporal factors and other external factors such as weather.