PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

On-line Learning
Peter Auer
(2007) Springer.

This is the latest version of this eprint.


In the on-line learning model the learner needs to make predictions sequentially, one after the other, and receives a reward or loss after each prediction. Typically, the learner receives some input before making a prediction. The goal of the learner is to maximize the accumulated rewards or minimize the accumulated losses, respectively.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Other
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
ID Code:6848
Deposited By:Peter Auer
Deposited On:08 March 2010

Available Versions of this Item