Please use this identifier to cite or link to this item:
Author(s): Henrique Lopes Cardoso
Eugénio Oliveira
Title: Using and evaluating adaptive agents in electronic commerce negotiation
Issue Date: 2000
Abstract: Agent technology has been applied to the Electronic Commercedomain, giving birth to what is known as agent-mediated Electronic Commerce.Current real-world applications refer only to the delegation of product ormerchant brokering tasks to software agents. Automated negotiation is a lessexplored stage in this field, since it implies the trust of bargaining power tosoftware agents. We here present SMACE, a layered platform for agentmediatedElectronic Commerce, supporting multilateral and multi-issueautomated negotiations. In this system, the negotiation infrastructure throughwhich the software agents interact is independent from their negotiationstrategies. SMACE has been used to test several negotiation strategies. Thesystem includes agents that are capable of increasing their performance withtheir own experience, by adapting to the market conditions. This adaptation isreached through the use of Reinforcement Learning techniques. In order to testthe agents' adaptation process, several different experiments have been triedout, and the respective results are here reported. These results allow us toconclude that it is possible to build negotiation strategies that can outperformothers in some environments. In fact, knowledge gath
Source: Advances in Artificial Intelligence
Document Type: Artigo em Livro de Atas de Conferência Internacional
Rights: restrictedAccess
Appears in Collections:FEUP - Artigo em Livro de Atas de Conferência Internacional

Files in This Item:
File Description SizeFormat 
  Restricted Access
83.8 kBAdobe PDF    Request a copy from the Author(s)

This item is licensed under a Creative Commons License Creative Commons