An anytime algorithm is an algorithm whose output increases in quality gradually with increased running time. This is in contrast to algorithms that produce no output at all until they produce full-quality output after a sufficiently long execution time. An example of an algorithm with good anytime performance is Adaptive Real-Time Dynamic Programming (ARTDP).
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this entry
Cite this entry
(2011). Anytime Algorithm. In: Sammut, C., Webb, G.I. (eds) Encyclopedia of Machine Learning. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-30164-8_23
Download citation
DOI: https://doi.org/10.1007/978-0-387-30164-8_23
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