See this document in CiteSeerX!

Solving Large MDPs Quickly with Partitioned Value Iteration (2003)  (Make Corrections)  
David Wingate, Kevin D. Seppi



  Home/Search   Context   Related

 
View or download:
byu.edu/papers/solvin...solving_mdps.ps
Cached:  PS.gz  PS  PDF   Image  Update  Help

From:  byu.edu/papers/solving_mdps/ (more)
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: Value iteration is not typically considered a viable algorithm for solving large-scale MDPs because it converges too slowly. However, the performance of value iteration can be dramatically improved by eliminating redundant or useless backups, and by backing up states in the right order. We present several methods designed to help structure value dependency, and present a systematic study of companion prioritization techniques (both atomic and hybrid) which focus computation in useful... (Update)

Similar documents based on text:   More   All
1.0:   P3VI: A Partitioned, Prioritized, Parallel Value Iterator - Wingate, Seppi (2004)   (Correct)
0.7:   Variable Resolution Discretization in the Joint Space - Monson, Wingate, Seppi..   (Correct)
0.6:   Efficient Value Iteration Using Partitioned Models - Wingate, Seppi   (Correct)

BibTeX entry:   (Update)

@misc{ wingate-solving,
  author = "David Wingate and Kevin D. Seppi",
  title = "Solving Large MDPs Quickly with Partitioned Value Iteration",
  url = "citeseer.ist.psu.edu/wingate03solving.html" }
Citations not processed or no citations identified.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC