Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
Formal analysis of decentralized decision making has become a thriving research area in recent years, producing a number of multi-agent extensions of Markov decision processes. Wh...
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...
This paper investigates how to automatically create a dialogue control component of a listening agent to reduce the current high cost of manually creating such components. We coll...
Toyomi Meguro, Ryuichiro Higashinaka, Yasuhiro Min...
— We consider decision-making problems in Markov decision processes where both the rewards and the transition probabilities vary in an arbitrary (e.g., nonstationary) fashion. We...