A Computational Architecture for a Pro-Social Rule Bending Agent

There have been many attempts to implement ethical reasoning in artificial agents. The principal philosophical approaches  attempted have been mainly deontological or utilitarian. Virtue ethics has been discussed but not thoroughly explored in implementations of ethical agents. A particularity of strict implementations of deontological/utilitarian approaches is that the results produced by these do not always conform to human intuitions of “the right thing to do”. Intuitions of the right thing to do in a particular social context are often independent of which philosophical school of thought human beings relate to. This is partly due to the ability of humans to step outside their particular reasoning framework, and make virtuous decisions based on what would be beneficial to society, not just themselves. This behaviour is called pro-social rule bending. This is a work-in-progress paper that details our attempt to implement pro-social rule bending in an artificial agent.