DMCA
Hybrid POMDP algorithms (2006)
| Venue: | In Proceedings of The Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM-2006 |
| Citations: | 8 - 3 self |
BibTeX
@INPROCEEDINGS{Paquet06hybridpomdp,
author = {Sébastien Paquet and Brahim Chaib-draa and Stéphane Ross},
title = {Hybrid POMDP algorithms},
booktitle = {In Proceedings of The Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM-2006},
year = {2006}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
When an agent evolves in a partially observable environment, it has to deal with uncertainties when choosing its actions. An efficient model for such environments is to use partially observable Markov decision processes (POMDPs). Many algorithms have been developed for POMDPs. Some use an offline approach, learning a complete policy before the execution. Others use an online approach, constructing the policy online for the current belief state. In this article, we present three hybrid algorithms that have been developed to combine the strengths of these two extremes approaches (offline and online). We present results showing that hybrid algorithms can often obtained better results than the online or the offline algorithms alone. 1
