The BDI models are among the best known agent's formalizations. They are based on the three mental attitudes: belief, desire and intention. Many of the BDI models do not admit degrees of belief, desire and intention. Parsons and Giorgini gave a semantic to the belief degree but not for desire and intention.The purpose of this paper is to continue the work of Parsons and Giorgini, by including desire and intention degrees. Another improvement of the BDI formalization is to add the emotion and physical state to the elements influencing the decision making. We illustrate the interaction between all these different concepts by proposing the (CDI)° architecture.
The Belief-Desire-Intention (BDI) model is a popular approach to design flexible agents. The key ingredient of BDI model, that contributed to concretize behavioral flexibility, is the inclusion of the practical reasoning. On the other hand, researchers signaled some missing flexibility’s ingredient, in BDI model, essentially the lack of learning. Therefore, an extensive research was conducted in order to extend BDI agents with learning. Although this latter body of research is important, the key contribution of BDI model, i.e., practical reasoning, did not receive a sufficient attention. For instance, for performance reasons, some of the concepts included in the BDI model are neglected by BDI architectures. Neglecting these concepts was criticized by some researchers, as the ability of the agent to reason will be limited, which eventually leads to a more or less flexible reasoning, depending on the concepts explicitly included. The current paper aims to stimulate the researchers to re-explore the concretization of practical reasoning in BDI architectures. Concretely, this paper aims to stimulate a critical review of BDI architectures regarding the flexibility, inherent from the practical reasoning, in the context of single agents, situated in an environment which is not associated with uncertainty. Based on this review, we sketch a new orientation and some suggested improvements for the design of BDI agents. Finally, a simple experiment on a specific case study is carried out to evaluate some suggested improvements, namely the contribution of the agent’s “well-informedness” in the enhancement of the behavioral flexibility.
BDI agents are among the most popular models for the development of intelligent agents. The practical reasoning within the most of BDI models and architectures rely, in the best case, on three kinds of attributes: The utility associated with a goal, the cost of a plan and the uncertainty associated with the action's effects. Based on a richer set of practical reasoning's attributes, we propose a BDI architecture which aims to provide a step towards more flexible BDI agents.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.