Show simple item record

dc.contributorXue, Yexiangen_US
dc.contributorToth, Russellen_US
dc.contributorDilkina, Bistraen_US
dc.contributorBernstein, Richarden_US
dc.contributorDamoulas, Theodorosen_US
dc.contributorClark, Patrick E.en_US
dc.contributorDe Gloria, Steveen_US
dc.contributorMude, Andrewen_US
dc.contributorBarrett, Christopheren_US
dc.contributorGomes, Carla P.en_US
dc.creatorErmon, Stefanoen_US
dc.identifier.citationStefano Ermon, Yexiang Xue, Russell Toth, Bistra Dilkina, Richard Bernstein, Theodoros Damoulas, Patrick E. Clark, Steve De Gloria, Andrew Mude, Christopher Barrett, Carla P. Gomes. (1/9/2015). Learning Large-Scale Dynamic Discrete Choice Models of Spatio-Temporal Preferences with Application to Migratory Pastoralism in East Africa. Palo Alto, United States: Association for the Advancement of Artificial Intelligence.en_US
dc.description.abstractUnderstanding spatio-temporal resource preferences is paramount in the design of policies for sustainable development. Unfortunately, resource preferences are often unknown to policy-makers and have to be inferred from data. In this paper we consider the problem of inferring agents’ preferences from observed movement trajectories, and formulate it as an Inverse Reinforcement Learning (IRL) problem . With the goal of informing policy-making, we take a probabilistic approach and consider generative models that can be used to simulate behavior under new circumstances such as changes in resource availability, access policies, or climate. We study the Dynamic Discrete Choice (DDC) models from econometrics and prove that they generalize the Max-Entropy IRL model, a widely used probabilistic approach from the machine learning literature. Furthermore, we develop SPL-GD, a new learning algorithm for DDC models that is considerably faster than the state of the art and scales to very large datasets. We consider an application in the context of pastoralism in the arid and semi-arid regions of Africa, where migratory pastoralists face regular risks due to resource availability, droughts, and resource degradation from climate change and development. We show how our approach based on satellite and survey data can accurately model migratory pastoralism in East Africa and that it considerably outperforms other approaches on a largescale real-world dataset of pastoralists’ movements in Ethiopia collected over 3 years.en_US
dc.publisherAssociation for the Advancement of Artificial Intelligenceen_US
dc.titleLearning Large-Scale Dynamic Discrete Choice Models of Spatio-Temporal Preferences with Application to Migratory Pastoralism in East Africaen_US
cg.creator.idMude, Andrew: 0000-0003-4903-6613en_US
cg.contributor.centerStanford Universityen_US
cg.contributor.centerCornell University - CORNELLen_US
cg.contributor.centerUniversity of Sydneyen_US
cg.contributor.centerGeorgia Techen_US
cg.contributor.centerNew York University, Center for Urban Science and Progress - NYU - CUSPen_US
cg.contributor.centerUnited States Department of Agriculture, Agricultural Research Service - USDA-ARSen_US
cg.contributor.centerInternational Livestock Research Institute - ILRIen_US
cg.contributor.crpCGIAR Research Program on Dryland Systems - DSen_US
cg.contributor.funderNot Applicableen_US
dc.identifier.statusOpen accessen_US

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

DSpace software copyright © 2002-2016  DuraSpace
MELSpace content providers and partners accept no liability to any consequence resulting from use of the content or data made available in this repository. Users of this content assume full responsibility for compliance with all relevant national or international regulations and legislation.
Theme by 
Atmire NV