Papers
2
Total Citations
7
H-Index
2
About
Mohand Hamadouche is a researcher focused on advancing autonomous decision-making, particularly for multi-agent robotic systems operating under uncertainty. His work centers on Markov Decision Processes (MDPs) and reinforcement learning, tackling the critical challenge of ensuring safe and efficient mission planning. A key contribution is his development of a "Reward Tuning" mechanism for self-adaptive policies in distributed MDPs, enabling multiple agents to coordinate actions while maintaining safety constraints—a vital step for real-world deployment in complex environments. His most cited work provides a practical comparative analysis of foundational algorithms like Value Iteration, Policy Iteration, and Q-Learning, offering clear guidance for solving sequential decision-making problems. While his citation counts (4 and 3 for his top papers) reflect an early-career stage, the direct relevance of his research to the growing fields of autonomous robotics and multi-agent systems signals a promising trajectory. Hamadouche’s contributions are particularly valuable for students and engineers seeking to bridge the gap between theoretical MDP models and robust, scalable implementations for real-world robotic missions.
Research Focus
Key Achievements
Top Papers
- 1
- 2