Maxwell Kolarich

Papers

Total Citations

H-Index

About

Maxwell Kolarich is a researcher in control theory and robotics, with a focus on data-driven methods for ensuring stability and convergence in dynamical systems. His most cited work, “Learning Contraction Policies From Offline Data” (2022), introduces a novel approach that leverages Contraction theory to synthesize control policies from pre-collected datasets. By ensuring that closed-loop system trajectories converge to a unique path, Kolarich’s method bridges offline learning and rigorous stability guarantees—a critical step for safe autonomous systems. Though early in his career, this contribution has already garnered attention (4 citations), reflecting its relevance in the growing field of learning-based control. Kolarich’s work stands out for its technical elegance: it transforms the challenge of certifying convergence into a tractable optimization problem, enabling practitioners to deploy policies without online exploration. His research holds promise for applications in robotics, aerospace, and any domain where reliable, data-efficient control is paramount. As the demand for verifiable AI in control systems rises, Kolarich’s contributions position him as a rising voice in the synthesis of learning and formal methods.