Ismail Saad

Universiti of Malaysia Sabah

Papers

1

Total Citations

39

H-Index

1

About

Ismail Saad is a leading researcher in deep reinforcement learning, with a focus on developing robust and stable algorithms for continuous control systems. His most-cited work, "Deep Reinforcement Learning with Robust Deep Deterministic Policy Gradient" (2020), addresses critical instability issues in the popular DDPG algorithm, which is widely applied in autonomous driving and robotics. By introducing novel techniques to enhance training stability, Saad’s contributions have directly improved the reliability of AI-driven decision-making in real-world environments. With 39 citations, this paper underscores his impact on the field, offering practical solutions that reduce dependency on hyperparameter tuning. Saad’s research bridges the gap between theoretical reinforcement learning and applied engineering, making his work essential for students and practitioners developing safer, more efficient autonomous systems. His achievements highlight a commitment to advancing AI robustness, positioning him as a key figure in the evolution of continuous control reinforcement learning.

Research Focus

Key Achievements

1
H-Index
1
Papers
39
Total Citations
39
Avg Citations/Paper
🏆 Most Cited Paper
Deep Reinforcement Learning with Robust Deep Deterministic Policy Gradient
39 citations · 2020
📈 Most Prolific Year: 2020 (1 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Universiti of Malaysia Sabah

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago