Persistent congestions which are varying in strength and duration in the dense traffic networks are the most prominent obstacle towards sustainable mobility. Those types of congestions cannot be adequately resolved by the traditional Adaptive Traffic Signal Control (ATSC). The introduction of Reinforcement Learning (RL) in ATSC as tackled those types of congestions by using on-line learning, which is based on the trial and error approach. Furthermore, RL is prone to the dimensionality curse related to the state–action space size based on which a non-linear quality function is derived. The Deep Reinforcement Learning (DRL) framework uses Deep Neural Networks (DNN) to digest raw traffic data to approximate the quality function of RL. This paper provides a comprehensive analysis of the most recent DRL approaches used for the ATSC algorithm design. Special emphasis is set to overview of the traffic state representation and multi-agent DRL frameworks applied for the large traffic networks. Best practices are provided for choosing the adequate DRL model, hyper-parameters tuning, and model architecture design. Finally, this paper provides a discussion about the importance of the open traffic data concept for the extensive application of DRL in the real world ATSC.

The problem with traffic congestion is particularly expressed in urban areas where possibilities for physical increment of capacity are limited or impossible. Significant in the approach to solving this problem is the usage of Public Transport (PT) and the implementation of various advanced control measures that can improve the quality of overall public transport system. The main objective of this research is to explore the possibilities of implementation of adaptive traffic control on signalized intersections giving priority to public transport vehicles through urban traffic network in the city of Zagreb. The possibilities of implementing public transport priority (PTP) technique in the city of Zagreb are analyzed because of specific traffic situations on defined corridors (location of stops, distance between intersections, etc.). With proper usage of PTP techniques (e.g. adequate detector positions, good estimation of PT vehicle arrival time at intersection) the total tram travel time can be significantly reduced. The Level of Service at intersection may be approximately retained because cross-street traffic demand was not ignored. According to technological level of traffic control system in the city of Zagreb, global implementation of PTP is not possible. So, for each intersection the PTP algorithm was developed separately, but mutual traffic influence of all intersections on the corridor was considered. The cooperative concept application within urban traffic control is considered as well.

Modern urban highways are under the influence of increased traffic demand and cannot fulfill the desired level of service anymore. In most of the cases there is no space available for any infrastructure building. Solutions from the domain of intelligent transport systems are used, such as ramp metering. To cope with the significant daily changes of the traffic demand, various approaches with autonomic properties like self-learning are applied for ramp metering. One of these approaches is reinforced learning. In this paper the Q-Learning algorithm is applied to learn the local ramp metering control law in a simulation environment, implemented in a VISSIM microscopic simulator. The approach proposed is tested in simulations with emphasis on the mainstream speed and travel time, using a typical on-ramp configuration.