Deniz Sen
Papers
2
Total Citations
8
H-Index
2
About
Deniz Sen is a researcher at the intersection of cognitive science and robotics, specializing in how sequential motor actions are learned and optimized. Their work draws inspiration from human motor control to improve robotic performance, particularly in tasks requiring precise, multi-step movements. Sen’s most cited paper, "A Critical Period for Robust Curriculum‐Based Deep Reinforcement Learning of Sequential Action in a Robot Arm" (2022, 6 citations), demonstrates that introducing a critical period—a concept from developmental neuroscience—can dramatically improve a robot arm’s ability to learn complex, context-dependent sequences through curriculum-based deep reinforcement learning. A second influential study, "Behavioral Optimization in a Robotic Serial Reaching Task Using Predictive Information" (2022, 2 citations), explores how predictive mechanisms, akin to human anticipation, can minimize errors and optimize control in serial reaching tasks. Together, these contributions highlight Sen’s novel approach of embedding biological learning principles into artificial systems, offering a path toward more adaptive and efficient robots. This work is particularly notable for bridging computational modeling with empirical insights from human motor behavior, making it highly relevant for researchers in embodied AI and neurorobotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2