Mostafa D. Awheda

Papers

Total Citations

H-Index

About

Mostafa D. Awheda is a researcher specializing in computational intelligence, with a primary focus on reinforcement learning, fuzzy logic systems, and their applications to differential games and autonomous control. His most cited work, "The residual gradient FACL algorithm for differential games" (2015, 18 citations), introduces a novel fuzzy reinforcement learning algorithm that simultaneously tunes both input and output parameters of a fuzzy logic controller. This algorithm employs three fuzzy inference systems (FISs)—one serving as an actor (fuzzy logic controller) and two as critics—to enhance learning stability and performance in dynamic, adversarial environments. By addressing the limitations of traditional gradient-based methods, Awheda’s approach improves convergence and robustness in differential game scenarios, making it valuable for robotics, autonomous systems, and adaptive control. His contributions bridge the gap between fuzzy logic and reinforcement learning, offering a more flexible and efficient framework for decision-making under uncertainty. Though his citation count reflects a focused niche, his work has been cited in studies on intelligent control and game theory, underscoring its relevance to advancing adaptive algorithms in complex, real-time systems.