Abstract
This paper first presents a new condition (C1) about the unbounded rewards under which the discounted optimality equation has a unique solution, then exposes sufficient conditions for the existence of a solution of the average optimality equation in the discrete time Markov decision processes. We also discuss the existence of (ε) optimal stationary policies. Finally, we use a simple method to deal with the continuous time Markov decision processes with average criterion.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
