Timely restoration of road networks plays a critical role in the response operations after disasters and helps communities turn back to their normal operations soon. Scarcity of restoration resources, uncertainty of recovery times, and behavioral variations of travelers are the major factors that highly complicate road network restoration operations. Here, these challenges are addressed by developing a Behaviorally-enriched Reinforcement Learning Mechanism (BRLM). Considering gradual adaptation of travelers, the mechanism optimizes scheduling and resource allocation decisions in the restoration process to make the highest acceleration in the post-disaster traffic movement. The performance of BRLM is tested on the road network of Sioux Falls in South Dakota for several tornado scenarios. To evaluate the efficiency of BRLM, a heuristic method is developed that ignores post-disaster traffic movement in making restoration decisions. Results show that the advantages of emergency road restoration on the post-disaster traffic flows completely depend on the behavior of travelers.
