Deliberative automated negotiators using fuzzy similarities

Automated agents are autonomous entities which de cide for themselves what when and under what con ditions their actions should be performed Since agents have no direct control over others they must persuade others to act in a particular manner The type of per suasion we consider in this paper is negotiation which we de ne as a process by which a joint decision is made by two or more parties The parties rst verbalise con tradictory demands and then move towards agreements Pruitt For negotiation agents must be provided with the ca pability to represent and reason about within their in formation and resource bounds both their internal and their external world and with the capacity to interact according to a normative protocol It is this individual agent modelling which has been the central focus of the work reported in this paper This paper extends our previous work reported in Faratin Sierra Jennings on negotiation mod els in the following way The agent architecture has been updated from a purely responsive mechanisms to include new higher level deliberative mechanisms in volving the generation of trade o s and the manipula tion of the set of issues under negotiation by means of a fuzzy similarity measure This paper advances the state of the art in negotiation by designing components of a negotiation architecture which allows agents to be both responsive and deliberative and thus participate in more varied types of negotiation processes The deliberative component of the individual agent architecture is expanded on which describe evaluation and o er generation mechanisms An example of a real world scenario is then introduced to clarify the con cepts introduced in the model Finally we present the conclusions reached and future avenues of research