The robbins-monro type stochastic differential equations. I. convergence of solutions

The Robbins-Monro (RM) type SDE is introduced, which naturally includes both generalized RM stochastic approximation algorithms with martingale noises and recursive estimationprocedures for general statistical models. The approach of the investigation of the a.s.convergence as of the strong solution of such type equations is proposed. The approach based on the new description of the semimartingales convergence sets andnonstandard representation of the process of bounded variation (in the decomposition of thespecial semimartingale in the form of difference of two increasing predictable processes