Learning from and about Other Agents in Terms of Social Metaphors

We present work that has been conducted in a sociological and psychological context. Our aim is to establish a mechanism that enables agents to cope with environments that contain mixtures of selfish and cooperative entities, where the mixture and the behaviour of these entities is previously unknown to all agents. We achieve this by enabling agents to evaluate trust in others, based upon the observations they gather. Using trust, they are able to request observations from others and make use of this possibly manipulated data, therefore enlarging their data base on behaviour of others. When using our approach, this results in significantly faster and better behaviour adaptation. We demonstrate the improvement in performance of agents using trust with the performance of others that just use their own observations.