Karthik Ganapathy
Papers
1
Total Citations
23
H-Index
1
About
Karthik Ganapathy is a rising researcher at the intersection of control theory, reinforcement learning, and robotics, with a focus on developing robust and data-efficient algorithms for decision-making under uncertainty. His most-cited work, "Policy Iteration for Linear Quadratic Games With Stochastic Parameters" (2020, 23 citations), bridges adversarial training and domain randomization—two pillars of modern robust machine learning—with classical control frameworks. By formalizing how policy iteration can handle stochastic parameter variations in linear quadratic games, Ganapathy provides a principled method for ensuring stability and performance in systems where model dynamics are uncertain or time-varying. This contribution is particularly valuable for safety-critical applications in robotics and autonomous systems, where robustness to environmental changes is paramount. His research elegantly connects theoretical guarantees from control theory with the practical demands of learning-based control, offering a pathway toward more reliable and adaptive autonomous agents. As an emerging scholar, Ganapathy is helping to shape how we design controllers that are both learning-capable and provably robust, a challenge at the heart of modern intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1Policy Iteration for Linear Quadratic Games With Stochastic Parameters23 citations · 2020