Toward socially responsible agents: integrating attachment and learning in emotional decision-making

摘要

Our goal is to create socially responsible agents, either robots or virtual humans. In this paper, we present an integration ofnemotions, attachment, and learning in emotional decision-making to achieve this goal. Based on emerging psychologicalntheories, we aim at building human-like emotional decision-making, where emotions play a central role in selecting thennext action to be performed by the agent. Here, we present our own approach for emotion appraisal where we use emotionalnattachment as an important impulse for determining the intensities of emotions. Emotions in their turn are used to calculatenthe emotional attachment toward the users and for learning to predict future consequences. We report on the results of ansimulation evaluation where we assess the influence of emotions, attachment, and learning on decision-making. It is ournstrong belief that by giving an agent the ability to have emotions and to feel empathy and emotional attachment towardnothers, we will ultimately give this agent the ability to learn and improve its social behavior skills through interactions withnthe users and through user feedback. Copyright © 2013 John Wiley & Sons, Ltd.