Molly Salman
Papers
1
Total Citations
27
H-Index
1
About
Molly Salman is a researcher at the intersection of reinforcement learning and nonlinear control theory, with a primary focus on developing safe, real-time decision-making algorithms for complex dynamical systems. Her most-cited work, "Continuous action reinforcement learning for control-affine systems with unknown dynamics" (2014, 27 citations), addresses a fundamental challenge in modern control: how to make split-second decisions that guarantee system safety when the underlying dynamics are poorly understood. Salman’s key contribution lies in bridging model-free reinforcement learning with control-theoretic guarantees, enabling autonomous systems—from robotic manipulators to drones—to learn optimal actions without solving intractable nonlinear differential equations. Her approach has proven particularly valuable for control-affine systems, where input constraints and safety margins must be respected in real time. While her citation count reflects a focused, technically deep body of work, Salman’s research is notable for its practical relevance to safety-critical applications, earning recognition among control theorists and machine learning engineers alike. For students and researchers, her work offers a compelling blueprint for marrying data-driven learning with rigorous control theory.
Research Focus
Key Achievements
Top Papers
- 1