Approximating Ergodic Average Reward Continuous-Time Controlled Markov Chains

作者：Prieto Rumeau Tomas^*; Maria Lorenzo Jose

来源：IEEE Transactions on Automatic Control, 2010, 55(1): 201-207.

DOI：10.1109/TAC.2009.2033848

• Approximation of control problems
• Ergodic Markov decision processes (MDPs)
• policy iteration algorithm

We study the approximation of an ergodic average reward continuous-time denumerable state Markov decision process (MDP) by means of a sequence of MDPs. Our results include the convergence of the corresponding optimal policies and the optimal gains. For a controlled upwardly skip-free process, we show some computational results to illustrate the convergence theorems.

• 出版日期2010-1