Papers
2
Total Citations
41
H-Index
2
About
Mariam Issa is a rising star in the field of intelligent control systems, with a primary focus on bridging the gap between classical robotics and modern Reinforcement Learning (RL). Her research addresses a critical challenge: how to make RL agents—typically reliant on resource-intensive deep neural networks—efficient enough to run on edge devices. In her highly cited 2022 paper "HDPG" (27 citations), Issa proposes a novel framework that infuses traditional continuous control methods with self-learning adaptability, moving beyond hand-crafted models toward more intelligent, human-level control. Her follow-up work, "DARL" (14 citations), directly tackles the computational bottleneck of modern RL by deploying alternative, lightweight models for powering agents on edge hardware. This work is pivotal for real-world applications where processing power is limited, such as in low-cost robotics and IoT devices. By demonstrating that sophisticated decision-making can be achieved without deep neural networks, Issa is paving the way for more accessible and energy-efficient autonomous systems. Her contributions are already shaping the next generation of resource-constrained AI, marking her as a key innovator in efficient, adaptive control.