A Theory of Goal-Oriented MDPs with Dead Ends

UAI, pp. 438-447, 2012.

Cited by: 71|Bibtex|Views42
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Stochastic Shortest Path (SSP) MDPs is a problem class widely studied in AI, especially in probabilistic planning. They describe a wide range of scenarios but make the restrictive assumption that the goal is reachable from any state, i.e., that dead-end states do not exist. Because of this, SSPs are unable to model various scenarios tha...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments