SEMI-MARKOV DECISION PROCESSES

M. Baykal-Gürsoy, K. Gürsoy
2007 Probability in the engineering and informational sciences (Print)  
Considered are semi-Markov decision processes (SMDPs) with finite state and action spaces. We study two criteria: the expected average reward per unit time subject to a sample path constraint on the average cost per unit time and the expected time-average variability. Under a certain condition, for communicating SMDPs, we construct (randomized) stationary policies that are e-optimal for each criterion; the policy is optimal for the first criterion under the unichain assumption and the policy is
more » ... n and the policy is optimal and pure for a specific variability function in the second criterion. For general multichain SMDPs, by using a state space decomposition approach, similar results are obtained.
doi:10.1017/s026996480700037x fatcat:djdhhjvqyjan7epuuz3p53fa6e