Skip to content

Incremental Delta Bar Delta (IDBD) algorithm for meta-learning the step-sizes

Notifications You must be signed in to change notification settings

vivekveeriah/IncrementalDeltaBarDelta

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Incremental Delta Bar Delta (IDBD)

IDBD is an algorithm for meta-learning step-sizes.

It was introduced by Rich Sutton in the following paper:

Sutton, R.S. (1992). Adapting bias by gradient descent: An incremental version of delta-bar-delta. Proceedings of the Tenth National Conference on Artificial Intelligence, pp. 171-176, MIT Press.

The code replicates an experiment from this paper.

About

Incremental Delta Bar Delta (IDBD) algorithm for meta-learning the step-sizes

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages