On a discrete-time stochastic learning control algorithm. (English) Zbl 1008.93069

It is shown that, if the product of the input/output coupling matrices is full-column rank, then the input error covariance matrix converges uniformly to zero in the presence of uncorrelated random disturbances, whereas the state error covariance matrix is not known. Furthermore, the convergence rate of the input error covariance matrix is shown to be inversely proportional to the number of learning iterations.


93E35 Stochastic learning and adaptive control
Full Text: DOI