Efficient Approximation of Optimal Control for Markov Games

Publication: Research - peer-reviewArticle in proceedings – Annual report year: 2011

Documents

View graph of relations

We study the time-bounded reachability problem for continuous-time Markov decision processes (CTMDPs) and games (CTMGs). Existing techniques for this problem use discretisation techniques to break time into discrete intervals, and optimal control is approximated for each interval separately. Current techniques provide an accuracy of O("2) on each interval, which leads to an infeasibly large number of intervals. We propose a sequence of approximations that achieve accuracies of O("3), O("4), and O("5), that allow us to drastically reduce the number of intervals that are considered. For CTMDPs, the performance of the resulting algorithms is comparable to the heuristic approach given by Buckholz and Schulz [6], while also being theoretically justified. All of our results generalise to CTMGs, where our results yield the first practically implementable algorithms for this problem. We also provide positional strategies for both players that achieve similar error bounds.
Original languageEnglish
Title of host publicationProceedings of the IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science
Publication date2011
StatePublished

Conference

ConferenceIARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science
CountryIndia
CityMumbai
Period12/12/1114/12/11
Download as:
Download as PDF
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
PDF
Download as HTML
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
HTML
Download as Word
Select render style:
APAAuthorCBEHarvardMLAStandardVancouverShortLong
Word

Download statistics

No data available

ID: 6305847