Sindhu Padakandla

About

Sindhu Padakandla is a leading researcher in reinforcement learning (RL), with a focus on developing algorithms that can adapt to dynamically changing environments. Her work addresses the critical gap between classical RL assumptions and the unpredictable, real-world conditions found in domains such as inventory control, cloud computing, and robotics. Her highly cited survey, “A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments” (2021, 211 citations), has become a foundational reference for researchers tackling non-stationary problems. Padakandla has also made notable contributions to autonomous UAV navigation, introducing memory-based deep RL techniques that enable quadrotors to avoid obstacles in unstructured indoor environments using only a monocular camera. This work, published in 2019, tackles the unique challenges of aerial robotics, such as limited environment knowledge and complex 3D dynamics. By bridging theoretical RL advances with practical deployment in UAVs and other autonomous systems, Padakandla’s research is shaping the next generation of adaptive, intelligent agents.

Research Focus

Key Achievements

Top Papers

1. 1
   A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments

   211 citations · 2021
2. 2
   Memory-Based Deep Reinforcement Learning for Obstacle Avoidance in UAV With Limited Environment Knowledge

   16 citations · 2019
3. 3
   Memory-based Deep Reinforcement Learning for Obstacle Avoidance in UAV\n with Limited Environment Knowledge

   2 citations · 2018

Key Collaborators

Contact & Links