Prioritization Methods for Accelerating MDP Solvers

The performance of value and policy iteration can be dramatically improved by eliminating redundant or useless backups, and by backing up states in the right order. We study several methods designed to accelerate these iterative solvers, including prioritization, partitioning, and variable reordering. We generate a family of algorithms by combining several of the methods discussed, and present extensive empirical evidence demonstrating that performance can improve by several orders of magnitude for many problems, while preserving accuracy and convergence guarantees. [abs] [ pdf ][ bib ] &copy JMLR 2005. ( edit, beta )

Authors

• David Wingate Satinder Baveja
• Kevin D. Seppi

Keywords

No keywords are indexed for this paper.