In computer science, the term “agent” usually denotes a software abstraction of a real entity which is capable of acting with a certain degree of autonomy. For example, in artificial societies, agents are software abstractions of real people, interacting in an artifical, simulated environment. Various authors have proposed different definitions of agents. Most of them would agree on the following set of agent properties:
Persistence: Code is not executed on demand but runs continuously and decides autonomously when it should perform some activity.
Social ability: Agents are able to interact with other agents.
Reactivity: Agents perceive the environment and are able to react.
Proactivity: Agents exhibit goal-directed behavior and can take the initiative.
This is a preview of subscription content, log in via an institution to check access.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
(2011). Agent. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_13
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_13
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30768-8
Online ISBN: 978-0-387-30164-8
eBook Packages: Computer ScienceReference Module Computer Science and Engineering