The precise specification of reward functions for Markov decision processes (MDPs) is often extremely difficult, motivating research into both reward elicitation and the robust so...
This paper investigates ‘complete ignorance’ (CI) in the tradition of the CI literature and provides a characterization of possible attitudes toward ignorance. Pessimism, opti...
Product recommendation and decision support systems must generally develop a model of user preferences by querying or otherwise interacting with a user. Recent approaches to elici...
The paper presents an efficient solution to decision problems where direct partial information on the distribution of the states of nature is available, either by observations of ...
Current conversational recommender systems are unable to offer guarantees on the quality of their recommendations due to a lack of principled user utility models. We develop an ap...