Shibl Mourad
Papers
1
Total Citations
38
H-Index
1
About
Shibl Mourad is a researcher whose work lies at the intersection of reinforcement learning and skill acquisition, with a particular focus on how agents can learn to combine existing behaviors to solve complex, long-horizon tasks. His most-cited paper, "The Option Keyboard: Combining Skills in Reinforcement Learning" (2019, 38 citations), introduces a novel framework for composing skills by defining them in the space of pseudo-rewards, or cumulants. This approach allows an agent to mix and match learned options—like pressing a key on a keyboard—to generate new, more sophisticated behaviors without retraining from scratch. Mourad’s contributions address a fundamental challenge in AI: enabling flexible, reusable skill composition in extended decision-making problems. His work has been influential in advancing hierarchical reinforcement learning, offering a principled method for skill transfer and combination that has inspired subsequent research in robotics and autonomous systems. With a clear focus on bridging theory and practical application, Mourad continues to explore how agents can leverage structured knowledge to adapt and generalize across diverse environments.
Research Focus
Key Achievements
Top Papers
- 1The Option Keyboard: Combining Skills in Reinforcement Learning38 citations · 2019