Managing Helpful Behavior in Collaborative Activities of Heterogeneous Agent Groups

This thesis aims to provide a foundation for designing computer agents able to work better with people and with other agents in heterogeneous groups. When agents work together on a collaborative activity, in addition to performing their share of the activity, they may be able to help one another and thus improve the collective utility. However, helpful actions typically result in some costs that may include resources consumed in communicating, lost opportunities to do other activities, the need for group members to adapt their individual plans to the helpful act or its effects, or interruption costs. The thesis specifically focuses on investigating the question of how, when and what kinds of helpful behavior should emerge when agents collaborate, taking into account the costs of a helpful action. It considers collaborative activities that take place in settings in which there is uncertainty about agents’ capabilities and about the state of the world. To ensure that helpful behavior improves the overall benefit of the collaboration, I have designed decision theoretic mechanisms that manage helpful behavior by considering the costs and utilities to both the agents and people participating in the collective action. For example, these mechanisms facilitate agents’ communication within a collaborative group as a type of helpful behavior. They increase efficiency of collaboration by better estimating the utility of helpful behavior