Preprint
Jul 2026
Direct Data Driven Natural Gradient Descent for Control
This paper proposes two data-driven NGD formulations that incorporate the closed-loop covariance matrix through the Fisher Information Matrix (FIM), allowing gradient updates to be preconditioned according to the system's intrinsic uncertainty.
Ramin Esmzad, F. Yaghmaie, Bahare Kiumarsi et al.
· 0 citations