Complexity of Decentralized Control: Special Cases
Abstract
The worst-case complexity of general decentralized POMDPs, which are equivalent to partially observable stochastic games (POSGs) is very high, both for the cooperative and competitive cases. Some reductions in complexity have been achieved by exploiting independence relations in some models. We show that these results are somewhat limited: when these independence assumptions are relaxed in very small ways, complexity returns to that of the general case.
Cite
Text
Allen and Zilberstein. "Complexity of Decentralized Control: Special Cases." Neural Information Processing Systems, 2009.Markdown
[Allen and Zilberstein. "Complexity of Decentralized Control: Special Cases." Neural Information Processing Systems, 2009.](https://mlanthology.org/neurips/2009/allen2009neurips-complexity/)BibTeX
@inproceedings{allen2009neurips-complexity,
title = {{Complexity of Decentralized Control: Special Cases}},
author = {Allen, Martin and Zilberstein, Shlomo},
booktitle = {Neural Information Processing Systems},
year = {2009},
pages = {19-27},
url = {https://mlanthology.org/neurips/2009/allen2009neurips-complexity/}
}