Optimal adaptive controllers based on least squares algorithms. (Chinese. English summary) Zbl 0846.93088
Summary: Optimal adaptive controllers based on input matching for stochastic systems are studied by using least-squares algorithms. The one-step-ahead least-squares method is established and the convergence rate of the parameter estimation is obtained. Without any exciting condition it is shown that the closed-loop system is globally stable and adaptive control converges to the one-step-ahead optimal control.
MSC:
93E24 | Least squares and related methods for stochastic control systems |
93E35 | Stochastic learning and adaptive control |
93E20 | Optimal stochastic control |