Target Value Criterion in Markov Decision Processes
Institution: | Universität Karlsruhe |
---|---|
Department: | |
Year: | 2014 |
Keywords: | Markov Decision Processes, Risk Sensitive Optimization, Target Value Criterion |
Record ID: | 1099425 |
Full text PDF: | http://digbib.ubka.uni-karlsruhe.de/volltexte/documents/3527201 |
We apply the Target Value Criterion to an MDP with a random planning horizon, derive an optimality equation and prove the existence of an optimal stationary policy in a generalized state space. The structure of the value function is exploited to approximate the target space by a finite subset and to derive upper and lower bounds as well as nearly optimal policies. As an extension we combine the Total Reward Criterion and the Target Value Criterion in a penalty approach.