Nafee Mourad

About

Nafee Mourad is a researcher advancing the field of interactive machine learning, with a focus on how robots and intelligent systems can learn effectively from imperfect human teachers. Her key research areas lie at the intersection of inverse reinforcement learning, Bayesian policy improvement, and human-robot interaction. Mourad’s major contribution is developing robust frameworks that allow learning systems to extract useful knowledge from sparse, non-optimal demonstrations and evaluative human feedback—a critical challenge in real-world applications where perfect demonstrations are rarely available. Her most-cited work, "Learning from Demonstrations and Human Evaluative Feedbacks" (2020, 20 citations), introduces an inverse reinforcement learning approach that handles both sparsity and imperfection in teaching signals. This is complemented by her earlier foundational paper, "Combination of learning from non-optimal demonstrations and feedbacks" (2018, 12 citations), which combines inverse reinforcement learning with Bayesian policy improvement to overcome suboptimal teaching. Mourad’s work is particularly notable for bridging the gap between theoretical learning algorithms and practical deployment, making her research highly relevant for students and engineers developing adaptive robotic systems that learn from natural human interaction.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning from Demonstrations and Human Evaluative Feedbacks: Handling Sparsity and Imperfection Using Inverse Reinforcement Learning Approach

   20 citations · 2020
2. 2
   Combination of learning from non-optimal demonstrations and feedbacks using inverse reinforcement learning and Bayesian policy improvement

   12 citations · 2018

Key Collaborators

Contact & Links