استراتژی پویای واگذاری تطبیقی ​​برای عوامل تجاری خودکار در بازار آزاد پویا

One of the crucial issues of automated negotiation in multi-agent systems is how to reach an agreement when a negotiation environment becomes open and dynamic. Even though some strategies have been proposed by researchers, most of them can only work within a static negotiation environment. In this paper, we present a model for designing a strategy for agents that makes adjustable rates of concession by negotiating according to the changes of environments with uncertain and dynamic outside options. This proposal is based on the market-driven agents (MDAs) model, and is guided by four factors in order to determine the degree of concession. These factors are trading opportunity, trading competition, trading time and strategy, and eagerness. The contribution of this paper is extending the MDAs model to an open and dynamic negotiation environment by considering both the current and potential changes of the environment.

Automated negotiation [20] has been an active research area in recent years. Research on negotiation agents [13] and [16] has received a great deal of attention in the areas of multi-agent systems and e-commerce [11] and [8]. Currently, one of the most crucial issues for automated negotiation is how to reach an agreement when the negotiation environment becomes open and dynamic. Although some agent-based systems [19], [3], [2], [10], [9], [26] and [17] have been proposed and implemented successfully by researchers, agents involved in these systems usually can only adopt predetermined strategies to negotiate with others. Therefore, when the negotiation environment is open and dynamic, such as more products and services becoming available and negotiators either entering or leaving the negotiation dynamically, agents cannot provide reasonable responses to changes in the negotiation environment by adopting their current negotiation strategies straightway. Furthermore, negotiators may also be bounded by restrictions such as deadlines and resource limitations. Agents may need to modify their negotiation strategies too when the pressure from these restrictions changes. The Market-Driven Agents (MDAs) model [22], [24], [23] and [18] is one strategy which takes into account the relationship between agents' negotiation strategies and the negotiation environment. Through comparing the MDAs model [23], [22] and [25] and other negotiation strategies

In this paper, four concession factors in MDAs (namely trading opportunity, trading competition, trading time and strategy and eagerness) are modified by taking into account uncertain and dynamic outside options. In an open and dynamic negotiation environment, negotiators are allowed to enter and leave a negotiation freely. Through analyzing the uncertain negotiation environment, the proposed approach can generate reasonable decisions to update agents' strategies in a dynamic environment. The experimental results also illustrate both the efficiency and accuracy of the proposed approach. In the future work, we are going to pursue more studies on multi-issue negotiation, because both the number of negotiation issues and agents' preferences will impact agents' attitudes to make concession during the negotiation. Also when the negotiation environment changes, agents' preferences will likely change. Therefore, we are trying to capture this fact and extend our approach by considering agents' preferences on each negotiation issue as the environment changes.