Computing Social Behaviours Using Agent Models

Agents can be thought of as following a social behaviour, depending on the context in which they are interacting. We devise a computationally grounded mechanism to represent and reason about others in social terms, reflecting the local perspective of an agent (first-person view), to support both stereotypical and empathetic reasoning. We use a hierarchy of agent models to discriminate which behaviours of others are plausible, and decide which behaviour for ourselves is socially acceptable, i. e. conforms to the social context. To this aim, we investigate the implications of considering agents capable of various degrees of theory of mind, and discuss a scenario showing how this affects behaviour.

Authors

• Paolo Felli University of Bologna
• Tim Miller The University of Melbourne
• Christian Muise Queen's University Vector Institute for Artificial Intelligence,
• Adrian R. Pearce
• Liz Sonenberg The University of Melbourne

Keywords

No keywords are indexed for this paper.