Risk-sensitive average continuous-time Markov decision processes with unbounded transition and cost rates

2021 ◽  
Vol 58 (2) ◽  
pp. 523-550
Author(s):  
Xin Guo ◽  
Yonghui Huang
Keyword(s):  
Markov Decision Processes ◽  
Continuous Time ◽  
Decision Processes ◽  
Finite Horizon ◽  
Dynamic Programming Principle ◽  
Iteration Algorithm ◽  
Stationary Policy ◽  
Risk Sensitive ◽  
Finite State ◽  
Markov Decision

AbstractThis paper considers risk-sensitive average optimization for denumerable continuous-time Markov decision processes (CTMDPs), in which the transition and cost rates are allowed to be unbounded, and the policies can be randomized history dependent. We first derive the multiplicative dynamic programming principle and some new facts for risk-sensitive finite-horizon CTMDPs. Then, we establish the existence and uniqueness of a solution to the risk-sensitive average optimality equation (RS-AOE) through the results for risk-sensitive finite-horizon CTMDPs developed here, and also prove the existence of an optimal stationary policy via the RS-AOE. Furthermore, for the case of finite actions available at each state, we construct a sequence of models of finite-state CTMDPs with optimal stationary policies which can be obtained by a policy iteration algorithm in a finite number of iterations, and prove that an average optimal policy for the case of infinitely countable states can be approximated by those of the finite-state models. Finally, we illustrate the conditions and the iteration algorithm with an example.

scholarly journals Policy Iteration for Continuous-Time Average Reward Markov Decision Processes in Polish Spaces

2009 ◽  
Vol 2009 ◽  
pp. 1-17 ◽  
Author(s):  
Quanxin Zhu ◽  
Xinsong Yang ◽  
Chuangxia Huang
Keyword(s):  
Markov Decision Processes ◽  
Continuous Time ◽  
Policy Iteration ◽  
Decision Processes ◽  
Iteration Algorithm ◽  
Average Reward ◽  
Stationary Policy ◽  
Optimality Equation ◽  
Markov Decision ◽  
Average Reward Optimality

We study thepolicy iteration algorithm(PIA) for continuous-time jump Markov decision processes in general state and action spaces. The corresponding transition rates are allowed to beunbounded, and the reward rates may haveneither upper nor lower bounds. The criterion that we are concerned with isexpected average reward. We propose a set of conditions under which we first establish the average reward optimality equation and present the PIA. Then under twoslightlydifferent sets of conditions we show that the PIA yields the optimal (maximum) reward, an average optimal stationary policy, and a solution to the average reward optimality equation.

scholarly journals New discount and average optimality conditions for continuous-time Markov decision processes

2010 ◽  
Vol 42 (04) ◽  
pp. 953-985 ◽  
Author(s):  
Xianping Guo ◽  
Liuer Ye
Keyword(s):  
Markov Decision Processes ◽  
Continuous Time ◽  
Average Cost ◽  
Nonnegative Solution ◽  
Decision Processes ◽  
Stationary Policy ◽  
Discounted Cost ◽  
Markov Decision ◽  
Optimal Stationary Policy ◽  
Bounded Below

This paper deals with continuous-time Markov decision processes in Polish spaces, under the discounted and average cost criteria. All underlying Markov processes are determined by given transition rates which are allowed to be unbounded, and the costs are assumed to be bounded below. By introducing an occupation measure of a randomized Markov policy and analyzing properties of occupation measures, we first show that the family of all randomized stationary policies is ‘sufficient’ within the class of all randomized Markov policies. Then, under the semicontinuity and compactness conditions, we prove the existence of a discounted cost optimal stationary policy by providing a value iteration technique. Moreover, by developing a new average cost, minimum nonnegative solution method, we prove the existence of an average cost optimal stationary policy under some reasonably mild conditions. Finally, we use some examples to illustrate applications of our results. Except that the costs are assumed to be bounded below, the conditions for the existence of discounted cost (or average cost) optimal policies are much weaker than those in the previous literature, and the minimum nonnegative solution approach is new.

scholarly journals New discount and average optimality conditions for continuous-time Markov decision processes

2010 ◽  
Vol 42 (4) ◽  
pp. 953-985 ◽  
Author(s):  
Xianping Guo ◽  
Liuer Ye
Keyword(s):  
Markov Decision Processes ◽  
Continuous Time ◽  
Average Cost ◽  
Nonnegative Solution ◽  
Decision Processes ◽  
Stationary Policy ◽  
Discounted Cost ◽  
Markov Decision ◽  
Optimal Stationary Policy ◽  
Bounded Below

This paper deals with continuous-time Markov decision processes in Polish spaces, under the discounted and average cost criteria. All underlying Markov processes are determined by given transition rates which are allowed to be unbounded, and the costs are assumed to be bounded below. By introducing an occupation measure of a randomized Markov policy and analyzing properties of occupation measures, we first show that the family of all randomized stationary policies is ‘sufficient’ within the class of all randomized Markov policies. Then, under the semicontinuity and compactness conditions, we prove the existence of a discounted cost optimal stationary policy by providing a value iteration technique. Moreover, by developing a new average cost, minimum nonnegative solution method, we prove the existence of an average cost optimal stationary policy under some reasonably mild conditions. Finally, we use some examples to illustrate applications of our results. Except that the costs are assumed to be bounded below, the conditions for the existence of discounted cost (or average cost) optimal policies are much weaker than those in the previous literature, and the minimum nonnegative solution approach is new.

scholarly journals Nonstationary value iteration in controlled Markov chains with risk-sensitive average criterion

2005 ◽  
Vol 42 (4) ◽  
pp. 905-918 ◽  
Author(s):  
Rolando Cavazos-Cadena ◽  
Raúl Montes-De-Oca
Keyword(s):  
Iteration Algorithm ◽  
Value Iteration ◽  
Stationary Policy ◽  
Long Run ◽  
Risk Sensitive ◽  
Finite State ◽  
Markov Decision ◽  
Optimal Stationary Policy ◽  
Compact Action Sets ◽  
Nonstationary Value Iteration

This work concerns Markov decision chains with finite state spaces and compact action sets. The performance index is the long-run risk-sensitive average cost criterion, and it is assumed that, under each stationary policy, the state space is a communicating class and that the cost function and the transition law depend continuously on the action. These latter data are not directly available to the decision-maker, but convergent approximations are known or are more easily computed. In this context, the nonstationary value iteration algorithm is used to approximate the solution of the optimality equation, and to obtain a nearly optimal stationary policy.

Sign in / Sign up

Export Citation Format

Share Document