Sadeq Mohammed Kadhm Sarkhi
Papers
2
Total Citations
9
H-Index
2
About
Sadeq Mohammed Kadhm Sarkhi is an emerging researcher at the forefront of artificial intelligence and game-based reinforcement learning. His work centers on optimizing deep reinforcement learning (DRL) models within complex, dynamic environments, with a particular focus on classic Atari games like Pac-Man. Sarkhi’s major contribution lies in pioneering the integration of advanced metaheuristic algorithms—specifically the Snake Optimization Algorithm and Energy Valley Optimization—into DRL frameworks. This novel approach addresses a critical bottleneck in gaming AI: the challenge of adapting and fine-tuning DRL agents for high-dimensional, unpredictable settings. His most cited paper (7 citations, 2024) demonstrates how these hybrid models significantly improve an agent’s decision-making and adaptability, outperforming traditional DRL methods. By bridging the gap between nature-inspired optimization and deep learning, Sarkhi’s work not only advances game-playing AI but also offers scalable solutions for broader sequential decision-making problems in robotics and autonomous systems. His research marks a promising step toward more efficient, robust, and intelligent agents capable of mastering complex real-world tasks.
Research Focus
Key Achievements
Top Papers
- 1
- 2