Agent-based negotiation teams are negotiation parties formed by more than a single individual. Individuals unite as a single negotiation party because they share a common goal that is related to a negotiation with one or several opponents. My research goal is providing agent-based computational models for negotiation teams in multi-agent systems.
This paper studies repetitive negotiation over the execution of an exploration process between two self-interested, fully rational agents in a full information environmentwith side payments. A key aspect of the protocolis that the exploration’s execution may interleaves ith the negotiation itself, inflicting some degradationon the exploration’s flexibility. The advantage of this form of negotiation is in enabling the agents supervising that the exploration’s execution takes place in its agreedform as negotiated. We show that in many cases, much of the computational complexity of the new protocol can be eliminated by solving an alternative negotiation scheme according to which the parties first negotiate theexploration terms as a whole and then execute it. As demonstrated in the paper, the solution characteristics of the new protocol are somehow different from thoseof legacy negotiation protocols where the execution of the agreement reached through the negotiation is completely separated from the negotiation process. Furthermore, if the agents are given the option to control some of the negotiation protocol parameters, the resulting exploration may be suboptimal. In particular we show that the increase in an agent’s expected utility in such casesis unbounded and so is the resulting decrease in the social welfare. Surprisingly, we show that further increasingone of the agents’ level of control in some of thenegotiation parameters enables bounding the resultingdecrease in the social welfare.
A large number of interdependent issues in complex contract negotiation poses a significant challenge for current approaches, which becomes even more apparent when negotiation problems scale up. To address this challenge, we present a structured anytime search process with an agenda management mechanism using a hierarchical negotiation model, where agents search at various levels during the negotiation with the guidance of a mediator. This structured negotiation process increases computational efficiency, making negotiations scalable for large number of interdependent issues. To validate the contributions of our approach, 1) we developed our proposed negotiation model using a hierarchical problem structure and a constraint-based preference model for real-world applications; 2) we defined a scenario matrix to capture various characteristics of negotiation scenarios and developed a scenario generator that produces test cases according to this matrix; and 3) we performed an extensive set of experiments to study the performance of this structured negotiation protocol and the influence of different scenario parameters, and investigated the Pareto efficiency and social welfare optimality of the negotiation outcomes. The experimental result supports the hypothesis that this hierarchical negotiation approach greatly improves scalability with the complexity of the negotiation scenarios.
Jonker, Catholijn M. (Delft University of Technology) | Hindriks, Koen V. (Delft University of Technology) | Wiggers, Pascal (Delft University of Technology) | Broekens, Joost (Delft University of Technology)
Negotiation is a complex emotional decision-making process aiming to reach an agreement to exchange goods or services. From an agent technological perspective creating negotiating agents that can support humans with their negotiations is an interesting challenge. Already more than a decade, negotiating agents can outperform human beings (in terms of deal optimality) if the negotiation space is well-understood. However, the inherent semantic problem and the emotional issues involved make that negotiation cannot be handled by artificial intelligence alone, and a human-machine collaborative system is required. This article presents research goals, challenges, and an approach to create the next generation of negotiation support agents.
From an agent technological perspective creating negotiating agents that can support humans with their negotiations is an interesting challenge. After more than a decade of research, negotiating agents can outperform human beings (in terms of deal optimality) if the negotiation space is well understood. However, the inherent semantic problem and the emotional issues involved mean that negotiation cannot be handled by artificial intelligence alone, and a human-machine collaborative system is required. This article presents research goals, challenges, and an approach to create the next generation of negotiation support agents. However, even professional negotiators can still improve their skills considerably.