This document discusses applying nonlinear stochastic optimal control (NSOC) theory to genetic algorithms (GA). It provides an overview of GA and NSOC, describes modeling GA as a discrete-time controlled Markov process within the NSOC framework, and presents the results of a numerical experiment applying the NSOC-described GA to optimization problems. The experiment shows the transition probabilities between states after 800 iterations, indicating individuals prefer moving to state 7. The document concludes by noting future work could improve the fitness function and computation speed when applying NSOC to GA.