Advanced methods of practicel reasoning in the BDI systems.

This dissertation topic is available for Czech studies only.

Practical decision making in a BDI system is based on the continuous building of a model of the agent's intentions and the subsequent execution of this model. The original computational system for BDI agents, the AgentSpeak(L) system, left room for further specification of some computational steps, such as choosing among multiple possible means to achieve goals, choosing intentions to execute, or choosing substitutions when performing formal inferences. It is the search for preferences in the choice of means and intentions that will be the focus of the work in this assignment. We anticipate using our original approach, which introduces late variable binding in the interpretation of AgentSpeak(L), which we hypothesize offers the possibility of outperforming current systems that address a similar problem. The result should be a system whose practical decision making exhibits a higher degree of rationality than that exhibited by currently existing BDI system solutions.