Beyond static snapshots: gated recurrent units and graph attention networks for smarter multi-agent traffic control
Existing multi-agent reinforcement learning (MARL) approaches for traffic signal control often fail to capture two critical characteristics of real-world urban traffic: the dynamic spatio-temporal propagation of congestion across intersections and the frequent imperfection of sensor data. To address these fundamental g...
Mohita, Sidak Deep Singh, D. Subitha et al.
· Frontiers in Artificial Inte... · 0 citations