This paper seeks to address the question of preference alignment in normative systems. We represent detached obligations and goals as preferences over outcomes, and describe when deterministic behaviour will occur within a MAS under specific system instantiations. We then investigate what obligations an agent with so called normative power should introduce in order to achieve their own goals.
|Number of pages||8|
|Publication status||Published - 1 Jan 2013|
|Event||25th Benelux Conference on Artificial Intelligence, BNAIC 2013 - Delft, Netherlands|
Duration: 7 Nov 2013 → 8 Nov 2013
|Conference||25th Benelux Conference on Artificial Intelligence, BNAIC 2013|
|Period||7/11/13 → 8/11/13|