Abdul Rahman Kreidieh

Papers

Total Citations

H-Index

About

Abdul Rahman Kreidieh is a leading researcher at the intersection of intelligent transportation systems and reinforcement learning, whose work is shaping the future of automated vehicular control. His primary contributions lie in developing scalable, data-driven frameworks to optimize complex, nonlinear dynamical systems—most notably traffic networks. Kreidieh’s landmark paper, “Unified Automatic Control of Vehicular Systems With Reinforcement Learning” (2022), with 54 citations, pioneers a deep reinforcement learning (DRL) approach to mitigate congestion and enhance efficiency in mixed-autonomy environments, where automated and human-driven vehicles coexist. This work demonstrates how DRL can unify control across diverse vehicular subsystems, offering a practical path toward real-world deployment. Additionally, his research on hierarchical reinforcement learning, as seen in “Inter-Level Cooperation in Hierarchical Reinforcement Learning” (2019), tackles the challenge of structured exploration in long-term planning by enabling temporally decoupled policies. Though less cited, this foundational work addresses a critical bottleneck in end-to-end training for multi-level policies. Kreidieh’s achievements are notable for bridging theoretical advances in RL with tangible applications in transportation, positioning him as a key figure in the push toward safer, more efficient automated mobility.