Stochastic planning for weakly-coupled distributed agents
A. Guo, and V. Lesser. AAMAS '06: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems, page 326--328. New York, NY, USA, ACM Press, (2006)
DOI: http://doi.acm.org/10.1145/1160633.1160689
Abstract
Partially observable stochastic games (POSGs) provide a powerful framework for modeling multi-agent interactions. While elegant and expressive, this framework has been shown to be computationally intractable 1. An exact dynamic programming algorithm for POSGs has been developed recently, but due to high computational demands, it has only been demonstrated to work on extremely small problems. Several approximate approaches have been developed 3, 5, but they lack strong theoretical guarantees. In light of these theoretical and practical limitations, there is a need to identify special classes of POSGs that can be solved tractably.
Description
: AAMAS '06, Stochastic planning for weakly-coupled ...
%0 Conference Paper
%1 conf/aamas06/Guo
%A Guo, AnYuan
%A Lesser, Victor
%B AAMAS '06: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems
%C New York, NY, USA
%D 2006
%I ACM Press
%K aamas06 agents planning
%P 326--328
%R http://doi.acm.org/10.1145/1160633.1160689
%T Stochastic planning for weakly-coupled distributed agents
%U http://portal.acm.org/citation.cfm?id=1160633.1160689&coll=ACM&dl=ACM&type=series&idx=1160633&part=Proceedings&WantType=Proceedings&title=International%20Conference%20on%20Autonomous%20Agents&CFID=25754815&CFTOKEN=92537800
%X Partially observable stochastic games (POSGs) provide a powerful framework for modeling multi-agent interactions. While elegant and expressive, this framework has been shown to be computationally intractable 1. An exact dynamic programming algorithm for POSGs has been developed recently, but due to high computational demands, it has only been demonstrated to work on extremely small problems. Several approximate approaches have been developed 3, 5, but they lack strong theoretical guarantees. In light of these theoretical and practical limitations, there is a need to identify special classes of POSGs that can be solved tractably.
%@ 1-59593-303-4
@inproceedings{conf/aamas06/Guo,
abstract = {Partially observable stochastic games (POSGs) provide a powerful framework for modeling multi-agent interactions. While elegant and expressive, this framework has been shown to be computationally intractable [1]. An exact dynamic programming algorithm for POSGs has been developed recently, but due to high computational demands, it has only been demonstrated to work on extremely small problems. Several approximate approaches have been developed [3, 5], but they lack strong theoretical guarantees. In light of these theoretical and practical limitations, there is a need to identify special classes of POSGs that can be solved tractably.},
added-at = {2007-08-03T14:50:25.000+0200},
address = {New York, NY, USA},
author = {Guo, AnYuan and Lesser, Victor},
biburl = {https://www.bibsonomy.org/bibtex/25f193d33f6e702c226576dd17a9b496c/mpfingst},
booktitle = {AAMAS '06: Proceedings of the fifth international joint conference on Autonomous agents and multiagent systems},
description = {: AAMAS '06, Stochastic planning for weakly-coupled ...},
doi = {http://doi.acm.org/10.1145/1160633.1160689},
interhash = {c759aff535a50a9ab2b54e8e9ce0965a},
intrahash = {5f193d33f6e702c226576dd17a9b496c},
isbn = {1-59593-303-4},
keywords = {aamas06 agents planning},
location = {Hakodate, Japan},
pages = {326--328},
publisher = {ACM Press},
timestamp = {2007-08-03T14:50:25.000+0200},
title = {Stochastic planning for weakly-coupled distributed agents},
url = {http://portal.acm.org/citation.cfm?id=1160633.1160689&coll=ACM&dl=ACM&type=series&idx=1160633&part=Proceedings&WantType=Proceedings&title=International%20Conference%20on%20Autonomous%20Agents&CFID=25754815&CFTOKEN=92537800},
year = 2006
}