Detecting the opportunities of learning from the interactions in a society of organizations

Abstract

Organizations, as any complex and inherently distributed entities, are characterized by their internal and external interactions. Generally, and as a result of the continuous interactive process, the involved organizations become more efficient This performance increase, achieved through resources optimization, can be seen as the outcome of a know-how acquired from previous interactions.

In broad terms, the work presented in this paper can be classified as a contribution to the study and modeling of the behavior of organizations. In particular, we are concerned with a specific inter-organization relation: the selection process that leads to the establishment of contracts between organizations. This selection process can be characterized as an iterative loop composed of an evaluation phase followed by a negotiation phase. During the selection activity, conflicts may occur imposing further negotiation as a mean for conflict resolution. According to the diverse selection methodologies that can be adopted, different learning opportunities can also be detected.

The computational system under development, which supports the above mentioned interaction processes, is called ARTOR (ARTificial ORganizations), and is based on the Distributed Artificial Intelligence — Multi-Agent Systems (DAI-MAS) and Symbolic Learning (SL) paradigms. Each component, or agent, is provided with the needed observation, planning, coordination, execution, communication and learning capabilities to perform its social role.