Georgiy Malaniya

Skolkovo Institute of Science and Technology

Papers

Total Citations

H-Index

About

Georgiy Malaniya is a researcher advancing the frontiers of reinforcement learning and stochastic control theory, with a focus on bridging the gap between discrete-time algorithms and continuous-time physical systems. His work addresses fundamental challenges in applying RL to real-world environments, where traditional Markov decision process models fall short. In his highly cited 2023 paper, "A Generalized Stacked Reinforcement Learning Method for Sampled Systems" (8 citations), Malaniya introduces a novel framework that extends RL to sampled-data systems, enabling more robust decision-making for time-continuous applications like robotics and autonomous vehicles. His 2022 study, "On Stochastic Stabilization via Nonsmooth Control Lyapunov Functions" (6 citations), tackles the critical issue of stabilization in nonholonomic systems—such as wheeled robots and cars—where control Lyapunov functions are inherently nonsmooth. By developing methods to handle these irregularities, Malaniya provides practical tools for ensuring stability under uncertainty. His contributions are particularly impactful for students and researchers working at the intersection of machine learning and control theory, offering new pathways for deploying RL in safety-critical, continuous-time domains.