— Humanoid robots are expected to share human environments in the future and it is important to ensure safety of their operation. A serious threat to safety is the fall of a huma...
We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
John Langford, Alexander L. Strehl, Jennifer Wortm...
Abstract. We consider policies that are described by regular expressions, finite automata, or formulae of linear temporal logic (LTL). Such policies are assumed to describe situat...
In this paper we consider how a BDI agent might determine its best course of action. We draw on previous work which has presented a model of persuasion over action and we discuss ...
Katie Atkinson, Trevor J. M. Bench-Capon, Peter Mc...
Members of high-performing human teams can often anticipate information needs of teammates and offer relevant information to them proactively. Such capabilities are highly desirab...