Paper Info
Title
A Matrix Splitting Perspective on Planning with Options.
Abstract
We show that the Bellman operator underlying the options framework leads to a matrix splitting, an approach traditionally used to speed up convergence of iterative solvers for large linear systems of equations. Based on standard comparison theorems for matrix splittings, we then show how the asymptotic rate of convergence varies as a function of the inherent timescales of the options. This new perspective highlights a trade-off between asymptotic performance and the cost of computation associated with building a good set of options.
Year
Venue
Field
2016
arXiv: Artificial Intelligence
Convergence (routing),Mathematical optimization,Linear system,Computer science,Matrix (mathematics),Operator (computer programming),Rate of convergence,Matrix splitting,Speedup,Computation
DocType
Volume
Citations 
Journal
abs/1612.00916
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
pierreluc bacon11069.68
Doina Precup22829221.83