Trading Performance for Stability in Markov Decision Processes
| Authors | |
|---|---|
| Year of publication | 2013 |
| Type | Article in Proceedings |
| Conference | Proceedings of 28th Annual ACM/IEEE Symposium on Logic in Computer Science (LICS 2013) |
| MU Faculty or unit | |
| Citation | |
| Doi | http://dx.doi.org/10.1109/LICS.2013.39 |
| Field | Informatics |
| Keywords | Markov decision processes; optimization |
| Description | We study the complexity of central controller synthesis problems for finite-state Markov decision processes, where the objective is to optimize both the expected mean-payoff performance of the system and its stability. We argue that the basic theoretical notion of expressing the stability in terms of the variance of the mean-payoff (called global variance in our paper) is not always sufficient, since it ignores possible instabilities on respective runs. For this reason we propose alernative definitions of stability, which we call local and hybrid variance, and which express how rewards on each run deviate from the run's own mean-payoff and from the expected mean-payoff, respectively. |
| Related projects: |