Abstract
When entering a system, an agent should be aware of the obligations and prohibitions (collectively norms) that will affect it. Existing solutions to this norm identification problem make use of observations of either other's norm compliant, or norm violating, behaviour.
However, they assume an extreme situation where norms are typically violated, or complied with.
In this paper we propose a Bayesian approach to norm identification which operates by learning from both norm compliant and norm violating behaviour. By utilising both types of behaviour, we not only overcome a major limitation of existing approaches, but also obtain improved performance over the state-of-the-art, allowing norms to be learned with a few observations. We evaluate the effectiveness of this approach empirically and discuss theoretical limitations to its accuracy.