Add to ORKGA 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
Fast self-tuning discrete-time control algorithms based on 'recursive least squares' parameter estim...
This paper presents a general approach: virtual equivalent system method to analyze the stability an...
AbstractThis paper develops an a.s. convergence theory for a class of projected stochastic approxima...
A recursive self-tuning control scheme for finite Markov chains is proposed wherein the unknown para...
For self-tuning control of a finite state Markov chain whose parametrized transition probabilities s...
In constrained Markov decision problems, optimal policies are often found to depend on quantities wh...
The self-tuning method of adaptive control for diffusions consists of estimating the unknown paramet...
The self-tuning method of adaptive control for diffusions consists of estimating the unknown paramet...
A class of feedback policies called finitely switched (FS) policies is introduced. When a one-dimens...
We consider an adaptive finite state controlled Markov chain with partial state information, motivat...
Consider a countable state controlled Markov chain whose transition probability is specified up to a...
The self-tuning approach to adaptive control is applied to a class of Markov chains called nearest-n...
In this paper, we developed the parametric estimation and the self-tuning control problem of the non...
A control problem for a partially observable Markov chain depending on a parameter with long run ave...
This paper investigates the problem of finite-time stabilization for a class of stochastic nonholono...
Fast self-tuning discrete-time control algorithms based on 'recursive least squares' parameter estim...
This paper presents a general approach: virtual equivalent system method to analyze the stability an...
AbstractThis paper develops an a.s. convergence theory for a class of projected stochastic approxima...
A recursive self-tuning control scheme for finite Markov chains is proposed wherein the unknown para...
For self-tuning control of a finite state Markov chain whose parametrized transition probabilities s...
In constrained Markov decision problems, optimal policies are often found to depend on quantities wh...
The self-tuning method of adaptive control for diffusions consists of estimating the unknown paramet...
The self-tuning method of adaptive control for diffusions consists of estimating the unknown paramet...
A class of feedback policies called finitely switched (FS) policies is introduced. When a one-dimens...
We consider an adaptive finite state controlled Markov chain with partial state information, motivat...
Consider a countable state controlled Markov chain whose transition probability is specified up to a...
The self-tuning approach to adaptive control is applied to a class of Markov chains called nearest-n...
In this paper, we developed the parametric estimation and the self-tuning control problem of the non...
A control problem for a partially observable Markov chain depending on a parameter with long run ave...
This paper investigates the problem of finite-time stabilization for a class of stochastic nonholono...
Fast self-tuning discrete-time control algorithms based on 'recursive least squares' parameter estim...
This paper presents a general approach: virtual equivalent system method to analyze the stability an...
AbstractThis paper develops an a.s. convergence theory for a class of projected stochastic approxima...