Utilizing partial policies for identifying equivalence of behavioral models

Yifeng Zeng, P. Doshi, Y. Pan, Hua Mao, M. Chandrasekaran, J. Luo

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

21 Citationer (Scopus)

Abstract

We present a novel approach for identifying exact and approximate behavioral equivalence between models of agents. This is significant because both decision making and game play in multiagent settings must contend with behavioral models of other agents in order to predict their actions. One approach that reduces the complexity of the model space is to group models that are behaviorally equivalent. Identifying equivalence between models requires solving them and comparing entire policy trees. Because the trees grow exponentially with the horizon, our approach is to focus on partial policy trees for comparison and determining the distance between updated beliefs at the leaves of the trees. We propose a principled way to determine how much of the policy trees to consider, which trades off solution quality for efficiency. We investigate this approach in the context of the interactive dynamic influence diagram and evaluate its performance.
OriginalsprogEngelsk
TitelProceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2011
RedaktørerWolfram Burgard, Dan Roth
Antal sider6
ForlagAAAI Press
Publikationsdato2011
Sider1083-1088
ISBN (Trykt)978-1-57735-507-6
StatusUdgivet - 2011
BegivenhedAAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference - San Francisco, USA
Varighed: 7 aug. 201111 aug. 2011
Konferencens nummer: 25/23

Konference

KonferenceAAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference
Nummer25/23
Land/OmrådeUSA
BySan Francisco
Periode07/08/201111/08/2011

Fingeraftryk

Dyk ned i forskningsemnerne om 'Utilizing partial policies for identifying equivalence of behavioral models'. Sammen danner de et unikt fingeraftryk.

Citationsformater