© 2011 Dr. David Nicholas Kinny ; About 5 years ago, the idea of software agents escaped from an obscure existence within the arcane field of Artificial Intelligence, and it is now running rampant through computer science, the software industry and the media, mutating violently as it goes and infecting many who come into contact with it. Despite humble origins in the study of Philosophy of Mind, the term agent has come to be applied to a diverse and disparate range of software constructs, and threatens soon to displace object from its primal position. Every computer scientist knows what agents are, or should be, although scant agreement upon definitions has been achieved, as so many variously qualified uses of the label now flourish. In the Artificial Intelligence research community where it was nurtured, however, the term still has a reasonably specific meaning: an agent is a situated or embedded system which participates in an ongoing interaction with some environment which it can observe and act upon. By assumption, an agent's behaviour is purposeful or motivated: it is thought of as wanting to perform some set of activities or achieve some set of goals and trying to do so when suitable opportunities present; in general it may be viewed as monitoring and controlling itself and its environment so as to bring about or maintain internal or external situations that it in some sense prefers. A very concrete example would be a robot, situated in the physical world, tasked to achieve certain objectives, but required to make its own moment-to-moment decisions about how and when to do so. But more often than not an agent inhabits an entirely artificial environment, within a single computer or a distributed network such as the Internet. It is with agents in this sense that this thesis is concerned. (From introduction)