Grigory Yaremenko
Papers
3
Total Citations
16
H-Index
2
About
Grigory Yaremenko is pioneering the intersection of reinforcement learning (RL) and control theory, with a sharp focus on stabilizing physical systems that operate in continuous time. His core research areas include model-free RL, stochastic stabilization, and nonsmooth control Lyapunov functions. Yaremenko’s major contribution is the development of the **Critic As Lyapunov Function (CALF)** agent—a model-free RL algorithm that guarantees online stabilization of dynamical systems during every learning episode, a breakthrough for safety-critical applications. His 2023 paper on a generalized stacked RL method for sampled systems (8 citations) extends RL beyond discrete-time video games to real-world, time-continuous environments. In 2022, he tackled the challenge of nonsmooth control Lyapunov functions (6 citations), essential for stabilizing nonholonomic systems like wheeled robots and cars. With 16 total citations across his most-cited works, Yaremenko is building a rigorous framework that ensures stability without requiring a system model—a vital step toward deploying RL in robotics, autonomous vehicles, and industrial control. His work is particularly notable for bridging the gap between theoretical Lyapunov stability and practical, data-driven learning.
Research Focus
Key Achievements
Top Papers
- 1A Generalized Stacked Reinforcement Learning Method for Sampled Systems8 citations · 2023
- 2On Stochastic Stabilization via Nonsmooth Control Lyapunov Functions6 citations · 2022
- 3