This paper contributes to the identification, formalisation and analysis of desirable properties of agent models in general and of the KGP model in particular. This model is specified in computational logic, and consequently lends itself well to formal analysis. We formalise three notions of welfare, in terms of goal achievement, progress, and reactive awareness, and we prove results related to these notions for KGP agents. These results broadly demonstrate the coherence of some of the design decisions in the KGP model, the need for some of its components for effectiveness in goal achievement, the extent to which the welfare of KGP agents can be shown to improve during their life-time, and the awareness of the agents of their reactions to changes in the environment.
pubs.doc.ic.ac.uk: built & maintained by Ashok Argent-Katwala.