NoisyNet + Double + Dueling + Prioritized Experience Replay + DQN (NP3DQN) on trafiic signal timing plan optimization, it can be used in an adaptive traffic control algorithm whereaa Dynamic Intersection Signal Control Optimisation (DISCO) as the virtual testbed on messo-simulation packages
a deep reinforcement learning network for traffic light cycle control
An agent-based learning towards decentralized and coordinated traffic signal control
Cooperative_Control_for_Multi-Intersection_Traffic_Signal_Based_on_Deep_Reinforcement_Learning_and_Imitation_Learning
Decentralized network level adaptive signal control by multi-agent deep reinforcement learning
Deep_Reinforcement_Learning_based_Traffic_Signal_optimization_for_Multiple_Intersections_in_ITS
Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Control
Traffic light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement learning
Traffic Signal Control with Cell Transmission Model Using Reinforcement Learning for Total Delay Minimisation
Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
A cold-start-free reinforcement learning approach for traffic signal control
NOISY NETWORKS FOR EXPLORATION