Title:
Learning task performance in market-based task allocation

dc.contributor.author Pippin, Charles, E. en_US
dc.contributor.author Christensen, Henrik I. en_US
dc.contributor.corporatename Georgia Tech Research Institute en_US
dc.contributor.corporatename Georgia Institute of Technology. College of Computing en_US
dc.contributor.corporatename Georgia Institute of Technology. Center for Robotics and Intelligent Machines en_US
dc.date.accessioned 2013-02-14T20:48:26Z
dc.date.available 2013-02-14T20:48:26Z
dc.date.issued 2012-06
dc.description © 2012 Springer-Verlag. The original publication is available at www.springerlink.com. en_US
dc.description Presented at the 12th International Conference on Intelligent Autonomous Systems (IAS-12) held June 26-29, 2012, Jeju Island, Korea. en_US
dc.description DOI: 10.1007/978-3-642-33932-5_57 en_US
dc.description.abstract Auction based algorithms offer effective methods for de-centralized task assignment in multi-agent teams. Typically there is an implicit assumption that agents can be trusted to effectively perform assigned tasks. However, reliable performance of team members may not always be a valid assumption. An approach to learning team member performance is presented, which enables more efficient task assignment. A policy gradient reinforcement learning algorithm is used to learn a cost factor that can be applied individually to auction bids. Experimental results demonstrate that agents that model team member performance using this approach can more efficiently distribute tasks in multi-agent auctions. en_US
dc.identifier.citation Pippin, C., and Christensen, H. I., “Learning task performance in market-based task allocation,” Proceedings of the 12th International Conference on Intelligent Autonomous Systems, IAS-12, June 26-29, 2012, Jeju Island, Korea, 613-621. en_US
dc.identifier.doi 10.1007/978-3-642-33932-5_57
dc.identifier.isbn 978-3-642-33931-8
dc.identifier.issn 2194-5357
dc.identifier.uri http://hdl.handle.net/1853/46195
dc.language.iso en_US en_US
dc.publisher Georgia Institute of Technology en_US
dc.publisher.original Springer-Verlag en_US
dc.subject Computational intelligence en_US
dc.subject Auction based algorithms en_US
dc.subject Market-based task allocation en_US
dc.subject Policy gradient reinforcement learning en_US
dc.title Learning task performance in market-based task allocation en_US
dc.type Text
dc.type.genre Proceedings
dc.type.genre Post-print
dspace.entity.type Publication
local.contributor.author Christensen, Henrik I.
local.contributor.corporatename Institute for Robotics and Intelligent Machines (IRIM)
relation.isAuthorOfPublication afdc727f-2705-4744-945f-e7d414f2212b
relation.isOrgUnitOfPublication 66259949-abfd-45c2-9dcc-5a6f2c013bcf
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
IAS12_PerfRL_Pippin.pdf
Size:
167.68 KB
Format:
Adobe Portable Document Format
Description: