The goal of this paper is to present a computational framework that enables us to generate elementary speech act sequences in a dialogue between an electronic assistant and a compu...
To increase the assurance with which agents can be deployed in operational settings, we have been developing the KAoS policy and domain services. In conjunction with Nomads strong...
Jeffrey M. Bradshaw, Andrzej Uszok, Renia Jeffers,...
Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
An agent that deviates from a usual or previous course of action can be said to display novel or varying behaviour. Novelty of behaviour can be seen as the result of real or appar...
: Other work has shown that adaptive learning can be highly successful in developing programs which are able to play games at a level similar to human players and, in some cases, e...