Recursive self-tuning control of finite Markov chains

Vivek Borkar
1997 Applicationes Mathematicae  
A recursive self-tuning control scheme for finite Markov chains is proposed wherein the unknown parameter is estimated by a stochastic approximation scheme for maximizing the log-likelihood function and the control is obtained via a relative value iteration algorithm. The analysis uses the asymptotic o.d.e.s associated with these. 1991 Mathematics Subject Classification: Primary 93E35.
doi:10.4064/am-24-2-169-188 fatcat:a4dnmzdg3bcqvmvu4hnwytwrvy