Skip to main content

BLGAN: Bayesian Learning and Genetic Algorithm for Supporting Negotiation With Incomplete Information

Sim, Kwang Mong (2009) BLGAN: Bayesian Learning and Genetic Algorithm for Supporting Negotiation With Incomplete Information. IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, 39 (1). pp. 198-211. ISSN 1083-4419. (doi:10.1109/TSMCB.2008.2004501) (KAR id:31929)

PDF
Language: English
Download (1MB) Preview
[img]
Preview
Official URL
http://dx.doi.org/10.1109/TSMCB.2008.2004501

Abstract

Automated negotiation provides a means for resolving

complete information, this paper provides mathematical proofs

its opponent’s reserve price (RP) and deadline. The impetus of

genetic algorithm (GA) to determine an agent’s optimal strategy

1) BL and a deadline-estimation process for estimating an opponent’s

at each negotiation round. Learning the RP and deadline of an

space (SP) by adaptively focusing its search on a specific region

as a region around an agent’s proposal P at each negotiation

using its estimations of its opponent’s RP and deadline.

that are closer to the proposal generated by the optimal strategy.

strategy, an agent in BLGAN compensates for possible errors in

that agents adopting BLGAN reached agreements successfully,

outcomes (CNOs) than agents that only adopt GA to generate their

only RP, and 3) higher utilities and better CNOs than agents that

do not learn their opponents’ RPs and deadlines.

Item Type: Article
DOI/Identification number: 10.1109/TSMCB.2008.2004501
Uncontrolled keywords: Automated negotiation, Bayesian learning (BL), genetic algorithms (GAs), intelligent agents, negotiation agents
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Faculties > Sciences > School of Computing > Data Science
Depositing User: Kwang Mong Sim
Date Deposited: 24 Oct 2012 10:31 UTC
Last Modified: 29 May 2019 09:40 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/31929 (The current URI for this page, for reference purposes)
  • Depositors only (login required):

Downloads

Downloads per month over past year