Value-Based Policy Teaching with Active Indirect Elicitation

DSpace/Manakin Repository

Value-Based Policy Teaching with Active Indirect Elicitation

Show simple item record

dc.contributor.author Zhang, Haoqi
dc.contributor.author Parkes, David C.
dc.date.accessioned 2010-05-03T14:10:54Z
dc.date.issued 2008
dc.identifier.citation Zhang, Haoqi and David C. Parkes. 2008. Value-based policy teaching with active indirect elicitation. In Proceedings of the Twenty-third AAAI Conference on Artificial Intelligence and the Twentieth Innovative Applications of Artificial Intelligence Conference: July 13-17, 2008, Chicago, Illinois, ed. American Association for Artificial Intelligence, 208-214. Menlo Park, Calif.: AAAI Press. en_US
dc.identifier.isbn 978-1-57735-368-3 en_US
dc.identifier.uri http://nrs.harvard.edu/urn-3:HUL.InstRepos:4039771
dc.description.abstract Many situations arise in which an interested party's utility is dependent on the actions of an agent; e.g., a teacher is interested in a student learning effectively and a firm is interested in a consumer's behavior. We consider an environment in which the interested party can provide incentives to affect the agent's actions but cannot otherwise enforce actions. In value-based policy teaching, we situate this within the framework of sequential decision tasks modeled by Markov Decision Processes, and seek to associate limited rewards with states that induce the agent to follow a policy that maximizes the total expected value of the interested party. We show value-based policy teaching is NP-hard and provide a mixed integer program formulation. Focusing in particular on environments in which the agent's reward is unknown to the interested party, we provide a method for active indirect elicitation wherein the agent's reward function is inferred from observations about its response to incentives. Experimental results suggest that we can generally find the optimal incentive provision in a small number of elicitation rounds. en_US
dc.description.sponsorship Engineering and Applied Sciences en_US
dc.language.iso en_US en_US
dc.publisher Association for the Advancement of Artificial Intelligence en_US
dc.relation.isversionof http://portal.acm.org/citation.cfm?id=1620030 en_US
dc.relation.hasversion http://www.eecs.harvard.edu/econcs/pubs/zp-aaai08.pdf en_US
dash.license LAA
dc.title Value-Based Policy Teaching with Active Indirect Elicitation en_US
dc.type Monograph or Book en_US
dc.description.version Accepted Manuscript en_US
dash.depositing.author Parkes, David C.
dc.date.available 2010-05-03T14:10:54Z

Files in this item

Files Size Format View
Zhang_Value.pdf 221.1Kb PDF View/Open

This item appears in the following Collection(s)

  • FAS Scholarly Articles [7218]
    Peer reviewed scholarly articles from the Faculty of Arts and Sciences of Harvard University

Show simple item record

 
 

Search DASH


Advanced Search
 
 

Submitters