A unified framework for temporal difference methods
We propose a unified framework for a broad class of methods to solve projected equations that approximate the solution of a high-dimensional fixed point problem within a subspace S spanned by a small number of basis functions or features. These methods originated in approximate dynamic programming (...
Main Author: | Bertsekas, Dimitri P. (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Laboratory for Information and Decision Systems (Contributor) |
Format: | Article |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers,
2010-10-01T18:17:46Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
A Unifying Polyhedral Approximation Framework for Convex Optimization
by: Bertsekas, Dimitri P., et al.
Published: (2011) -
Pathologies of Temporal Difference Methods in Approximate Dynamic Programming
by: Bertsekas, Dimitri P.
Published: (2011) -
Convergence Results for Some Temporal Difference Methods Based on Least Squares
by: Yu, Huizhen, et al.
Published: (2012) -
Approximate policy iteration: A survey and some new methods
by: Bertsekas, Dimitri P.
Published: (2012) -
Incremental proximal methods for large scale convex optimization
by: Bertsekas, Dimitri P.
Published: (2012)