Encyclopedia of Machine Learning

2010 Edition
| Editors: Claude Sammut, Geoffrey I. Webb


Reference work entry
DOI: https://doi.org/10.1007/978-0-387-30164-8_178

In  Markov decision processes, negative rewards are often expressed as costs. A reward of − x is expressed as a cost of x. In  supervised learning, cost is used as a synonym for  loss.

Cross References


Copyright information

© Springer Science+Business Media, LLC 2011