Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, t...
The POMDP is considered as a powerful model for planning under uncertainty. However, it is usually impractical to employ a POMDP with exact parameters to model precisely the real-...
Abstract. We consider an upper confidence bound algorithm for Markov decision processes (MDPs) with deterministic transitions. For this algorithm we derive upper bounds on the onl...