Eugene A. Feinberg, Jefferson Huang
Published 2015-07-02Version 1
This paper provides conditions under which countable-state total-cost and average-cost Markov decision processes (MDPs) can be reduced to discounted ones. Results are given for transient total-cost MDPs with transition rates that are not necessarily probabilities, as well as for average-cost MDPs with transition probabilities satisfying the condition that there is a state such that the expected time to reach it is uniformly bounded for all initial states and stationary policies. When the state and action sets are finite, these reductions lead to linear programming formulations and complexity estimates for MDPs under the aforementioned criteria.
Reduction of total-cost and average-cost MDPs with weakly continuous transition probabilities to discounted MDPs
Average-Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
On the Minimum Pair Approach for Average-Cost Markov Decision Processes with Countable Discrete Action Space and Strictly Unbounded Costs
![QR code for arXiv:1507.00664 [math.OC]](http://oss.arxitics.com/images/favicon.svg)