Exploration and Exploitation in Adaptive Trust-Based Decision Making in Dynamic Environments

Trust is generally considered an important aspect in the decision making of agents. In the literature, a variety of computational models for trust have been proposed covering how an agent can make a decision by exploiting the trust levels it has for the different options. Within such a decision making mechanism the focus is usually on a single most trusted option, which as a side effect may lead to a lack of information on the other options over time. Therefore it may sometimes be worthwhile to be more explorative in the decision making, especially for dynamic environments. In this paper an adaptive trust-based decision making model is proposed that varies the extent of exploration and exploitation in the agent´s decisions.