Output details
11 - Computer Science and Informatics
University of Kent
Evolving Fuzzy Rules for Relaxed-Criteria Negotiation
<22> This work was published in a top IEEE Journal (acceptance rate:7%). Whereas existing works on negotiation in simpler market settings focused only on optimizing utilities, this work introduced a new branch of thinking for solving much more difficult negotiation problems by devising negotiation agents that use heuristics to improve success rates and negotiation speed and can evolve their structures by learning new fuzzy rules. Favorable empirical results validated that self-evolving agents improve their negotiation outcomes as they participate in negotiations in more e-markets. It led to work by other groups (e.g., BeijingUTech) on evolving optimized parameters of fuzzy rules.