基于多Agent协商的虚拟企业伙伴选择方法

伙伴选择是虚拟企业建立过程中的核心问题,分析了虚拟企业的特点、虚拟企业环境下协商问题的特点,提出了一个适合于虚拟企业环境的多Agent协商模型。该模型支持多Agent多议题的多轮谈判,并将Agent类型引入到协商中来,作为指导协商Agent提议的一个重要因素。在不完全信息的条件下,应用贝叶斯学习的方法,更新既有信息,并通过分析对方Agent的历史提议序列,推测其类型,来指导自身的提议策略和战术,使自己的提议更具有针对性,避免了盲目性,从而节约协商时间,提高了协商的效率,使得盟主企业能在尽短的时间里寻找到理想的合作伙伴。     

一种多Agent多议题的协商模型

协商是多Agent系统实现协作、协调和冲突消解的关键技术。本文分析了协商问题的实质和协商过程,提出了一种支持多轮协商的多Agent多议题协商模型。模型中引入了Agent类型的概念,在信息不完全的条件下,协商Agent通过推测协商对手的类型来指导自身的提议策略和协商战术,使提议更具针对性,避免了盲目性,从而节约了协商时间,提高了协
商质量。     

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

Automated negotiation provides a means for resolving differences among interacting agents. For negotiation with complete information, this paper provides mathematical proofs to show that an agent's optimal strategy can be computed using its opponent's reserve price (RP) and deadline. The impetus of this work is using the synergy of Bayesian learning (BL) and genetic algorithm (GA) to determine an agent's optimal strategy in negotiation (N) with incomplete information. BLGAN adopts: (1) BL and a deadline-estimation process for estimating an opponent's RP and deadline and (2) GA for generating a proposal at each negotiation round. Learning the RP and deadline of an opponent enables the GA in BLGAN to reduce the size of its search space (SP) by adaptively focusing its search on a specific region in the space of all possible proposals. SP is dynamically defined as a region around an agent's proposal P at each negotiation round. P is generated using the agent's optimal strategy determined using its estimations of its opponent's RP and deadline. Hence, the GA in BLGAN is more likely to generate proposals that are closer to the proposal generated by the optimal strategy. Using GA to search around a proposal generated by its current strategy, an agent in BLGAN compensates for possible errors in estimating its opponent's RP and deadline. Empirical results show that agents adopting BLGAN reached agreements successfully, and achieved: (1) higher utilities and better combined negotiation outcomes (CNOs) than agents that only adopt GA to generate their proposals, (2) higher utilities than agents that adopt BL to learn only RP, and (3) higher utilities and better CNOs than agents that do not learn their opponents' RPs and deadlines.     

Pre-argumentative reasoning

Intelligent agents configure a new generation of virtual entities that perform various autonomous tasks on behalf of others, namely the humans. On the other hand, the information society requires the development of new and more intelligent methods, tools and theories to analyse, define, model and specify agent-based systems. It is under this presupposition that in this work are introduced a pre-argumentative reasoning scheme, which need to be able to take into account, in a negotiation, factors such as temporality, priority, delegation, gratitude and agreement, enabling the agents to react and pro-act accordingly. This argument-based negotiation among agents has much to gain from the use of Extended Logic Programming and Incomplete Information, in terms of the argument's evaluation. Indeed, it is based on this substratum that are presented the bases for a pre-contract negotiation via argumentation, where pre-contract negotiation will be defined as a protocol which, once enforced, will allow the exchange of messages containing proposals, counter-proposals, critiques, justifications or even explanations. The terms of a negotiation are also set, adjusting the contract according to the agent's knowledge base. In fact, an important contribution of this work relies on the presentation of the basic definitions and the general model of pre-contract-based negotiations via argumentation.     

Continuous-Time Negotiation Mechanism for Software Agents

While there are several existing mechanisms and systems addressing the crucial and difficult issues of automated one-to-many negotiation, this paper develops a flexible one-to-many negotiation mechanism for software agents. Unlike the existing general one-to-many negotiation mechanism, in which an agent should wait until it has received proposals from all its trading partners before generating counterproposals, in the flexible one-to-many negotiation mechanism, an agent can make a proposal in a flexible way during negotiation, i.e., negotiation is conducted in continuous time. To decide when to make a proposal, two strategies based on fixed waiting time and a fixed waiting ratio is proposed. Results from a series of experiments suggest that, guided by the two strategies for deciding when to make a proposal, the flexible negotiation mechanism achieved more favorable trading outcomes as compared with the general one-to-many negotiation mechanism. To determine the amount of concession, negotiation agents are guided by four mathematical functions based on factors such as time, trading partners' strategies, negotiation situations of other threads, and competition. Experimental results show that agents guided by the four functions react to changing market situations by making prudent and appropriate rates of concession and achieve generally favorable negotiation outcomes     

Using similarity criteria to make issue trade-offs in automated negotiations

Automated negotiation is a key form of interaction in systems that are composed of multiple autonomous agents. The aim of such interactions is to reach agreements through an iterative process of making offers. The content of such proposals are, however, a function of the strategy of the agents. Here we present a strategy called the trade-off strategy where multiple negotiation decision variables are traded-off against one another (e.g., paying a higher price in order to obtain an earlier delivery date or waiting longer in order to obtain a higher quality service). Such a strategy is commonly known to increase the social welfare of agents. Yet, to date, most computational work in this area has ignored the issue of trade-offs, instead aiming to increase social welfare through mechanism design. The aim of this paper is to develop a heuristic computational model of the trade-off strategy and show that it can lead to an increased social welfare of the system. A novel linear algorithm is presented that enables software agents to make trade-offs for multi-dimensional goods for the problem of distributed resource allocation. Our algorithm is motivated by a number of real-world negotiation applications that we have developed and can operate in the presence of varying degrees of uncertainty. Moreover, we show that on average the total time used by the algorithm is linearly proportional to the number of negotiation issues under consideration. This formal analysis is complemented by an empirical evaluation that highlights the operational effectiveness of the algorithm in a range of negotiation scenarios. The algorithm itself operates by using the notion of fuzzy similarity to approximate the preference structure of the other negotiator and then uses a hill-climbing technique to explore the space of possible trade-offs for the one that is most likely to be acceptable.     

多Agent谈判：一种基于模糊逻辑控制的方法

在分析各种Agent谈判模型不足的基础上，首先给出基于黑板模式的谈判Agent体系结构，然后设计了一个通用的谈判Agent建议的综合评价方法。此外，应用标准可加性模型原理设计了谈判Agent的策略模型，从而构建了应用范围广泛的自动化谈判Agent模型。     

多Agent多问题协商模型

在多agent环境中,协商是多agent系统能够成功运转的关键.根据参与协商agent的数目和协商问题的数目,多agent环境中的协商可以分为双边-单问题协商、双边-多问题协商、多边-单问题协商、多边-多问题协商.前3种协商是多边-多问题协商在不同维上的简化.利用协商-协商过程-协商线程的概念建立了一个多边-多问题协商模型MMN(multi-agent multi-issue negotiation).该模型通过提供一个灵活的协商协议支持多agent环境中的不同协商形式,并且支持agent在协商过程中的学习.     

制造业供应链产销协同计划冲突协商模型

面对市场竞争日益剧烈和客户需求多样化的趋势,制造业供应链的制造商和经销商努力实现产销协同计划。然而在产销协同计划中时常出现冲突,及时有效消解冲突,能提高整个供应链的协作效率,改善供应链上企业间的合作关系;反之,会降低供应链的运作效率,削弱供应链的竞争力。针对这类冲突问题,引入让步协商策略,在有限信息共享条件下,建立供应链产销协同计划冲突协商模型;设计具有历史提议回顾特点的协商流程;通过文化基因算法,产生反提议生成策略;通过算例验证文化基因算法及冲突协商模型的有效性。