We address the problem of the development of representations by an agent and its relationship to the environment. A software agent develops a representation of its environment through a network, which captures and integrates the relationships between agent and environment through a closure mechanism. A variable behavior modifier improves the representation development. We report the preliminary results where we analyze two aspects: 1) The structural properties of the resulting representation can be used as indicators of the knowledge assimilated by the agent from the interaction with the environment. These properties can be taken as useful macrovariables from an objective point of view; and 2) The dynamics of the closure mechanism, can be seen as the internal, and therefore subjective, way used by the system to develop its representation. We are not interested only on how the mechanism functions, but also on how the representation evolves. ©Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
De La Mora, C. R. B., Gershenson, C., & García-Vega, V. A. (2004). Representation development and behavior modifiers. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3315, pp. 504–513). https://doi.org/10.1007/978-3-540-30498-2_50
Mendeley helps you to discover research relevant for your work.