Maithili Shetty

Papers

Total Citations

H-Index

About

Maithili Shetty is a robotics researcher whose work focuses on advancing deep reinforcement learning (DRL) for continuous control in robotic manipulation. Her primary research areas include reinforcement learning algorithms, robot control systems, and the application of deep learning to high-dimensional state and action spaces. Shetty’s most notable contribution is her exploration of the Deep Deterministic Policy Gradient (DDPG) algorithm, which addresses key limitations of earlier RL methods by enabling stable, sample-efficient learning in continuous action domains. Her 2021 paper on this topic, which has garnered 1 citation, demonstrates how DDPG can effectively control robot manipulators—a critical step toward more autonomous and adaptable industrial and service robots. While her citation count is modest, her work represents foundational progress in bridging the gap between simulated RL training and real-world robotic applications. Shetty’s research is particularly valuable for students and engineers seeking to understand how modern DRL techniques can overcome the curse of dimensionality and action-space discretization, offering a clear pathway to more fluid, human-like robot motion. Her contributions underscore the growing importance of model-free, continuous control algorithms in next-generation robotics.