Show simple item record

dc.contributor.authorParkes, David C.
dc.contributor.authorGreenwald, Lloyd
dc.date.accessioned2010-05-18T19:16:02Z
dc.date.issued2001
dc.identifier.citationParkes, David C., and Lloyd Greenwald. 2001. Approximate and compensate: A method for risk-sensitive meta-deliberation and continual computation. In Using uncertainty within computation: Papers from the 2001 AAAI Fall Symposium: November 2-4, 2001, North Falmouth, Massachusetts, ed. C. Gomes, T. Walsh, and American Association for Artificial Intelligence, 101-108. Menlo Park, C.A.: AAAI Press.en_US
dc.identifier.isbn9781577351382en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:4101699
dc.description.abstractWe present a flexible procedure for a resource-bounded agent to allocate limited computational resources to on-line problem solving. Our APPROXIMATE AND COMPENSATE methodology extends a well-known greedy time-slicing approach to conditions in which performance profiles may be non-concave and there is uncertainty in the environment and/or problem-solving procedures of an agent. With this method, the agent first approximates problem-solving performance and problem parameters with standard parameterized models. Second, the agent computes a risk-management factor that compensates for the risk inherent in the approximation. The risk-management factor represents a mean-variance tradeoff that may be derived optimally off-line using any available information. Theoretical and experimental results demonstrate that APPROXIMATE AND COMPENSATE extends existing methods to new problems and expands the practical application of meta-deliberation.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.language.isoen_USen_US
dc.publisherAssociation for the Advancement of Artificial Intelligenceen_US
dc.relation.isversionofhttps://www.aaai.org/Papers/Symposia/Fall/2001/FS-01-04/FS01-04-016.pdfen_US
dc.relation.hasversionhttp://www.eecs.harvard.edu/econcs/pubs/approxcomp.pdfen_US
dash.licenseLAA
dc.titleApproximate and Compensate: A Method for Risk-Sensitive Meta-Deliberation and Continual Computationen_US
dc.typeMonograph or Booken_US
dc.description.versionAccepted Manuscripten_US
dash.depositing.authorParkes, David C.
dc.date.available2010-05-18T19:16:02Z
dash.contributor.affiliatedParkes, David


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record