Markov decision Processes with fractional costs
Zhiyuan Ren, Bruce H. Krogh · IEEE Transactions on Automatic Control · 2005
Certain methods for constructing embedded Markov decision processes (MDPs) lead to performance measures that are the ratio of two long-run averages. For such MDPs with finite state and action spaces and under an ergodicity assumption, this note presents algorithms for computing optimal policies based on policy iterations, linear programming, value iterations and Q-learning.