The Benefits of Opponent Models in Negotiation

Hindriks, Koen V.; Jonker, Catholijn M.; Tykhonov, Dmytro

doi:10.1109/wi-iat.2009.192

Cited by 23 publications

(27 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various machine learning techniques are used for opponent modelling, for example, to gain more information on the zone of agreement (Zeng and Sycara, 1997) or on the shape of the evaluation functions per issue (Hindriks et al, 2009). …”

Section: Preference Profile Predictabilitymentioning

confidence: 99%

From problems to protocols: Towards a negotiation handbook

Marsa-Maestre

Klein

Jonker

et al. 2014

Decision Support Systems

Self Cite

View full text Add to dashboard Cite

Automated negotiation protocols represent a potentially powerful tool for problem solving in decision support systems involving participants with conflicting interests. However, the effectiveness of negotiation approaches depends greatly on the negotiation problem under consideration. Since there is no one negotiation protocol that clearly outperforms all others in all scenarios, we need to be able to decide which protocol is most suited for each particular problem. The goal of our work is to meet this challenge by defining a "negotiation handbook", that is, a collection of design rules which allow us, given a particular negotiation problem, to choose the most appropriate protocol to address it. This paper describes our progress towards this goal, including a tool for generating a wide range of negotiation scenarios, a set of high-level metrics for characterizing how negotiation scenarios differ, a testbed environment for evaluating protocol performance with different scenarios, and a community repository which allows us to systematically record and analyze protocol performance data.

show abstract

Section: Preference Profile Predictabilitymentioning

confidence: 99%

From problems to protocols: Towards a negotiation handbook

Marsa-Maestre

Klein

Jonker

et al. 2014

Decision Support Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…As compared to this system, in our approach, there are several negotiation strategies, which can be changed during negotiation, and the negotiation domain is specified by the agent rules. A negotiation strategy that describes a method to learn a model of opponent preferences in a single negotiation session is presented in [13]. The negotiation strategy should be efficient, transparent, maximizing the chance of an agreement and should avoid exploitation.…”

Section: Real Estate Agency Automated Negotiation Businessmentioning

confidence: 99%

Bargain strategies for agent automated negotiation in an e-business environment

Serban¹,

Florea²

2014

SCPE

View full text Add to dashboard Cite

Abstract. An automated negotiation environment, in which agents employ different bargaining strategies is described. During negotiation, as more information is exchanged in the negotiation rounds, the agents can change the preferences for certain attributes of the negotiation object. The multi-agent system is developed for a real estate agency business model and several use cases scenarios, using intelligent software agents, are implemented.Key words: automated negotiation, multi-agent system, negotiation strategy AMS subject classifications. 68T42, 68T05, 68T351. Introduction. Negotiation is an important issue in business environments. Automated negotiation is a process, in which software agents communicate between them, in order to reach a mutually acceptable agreement [1]. An intelligent agent should be able to negotiate with other agents, which have different negotiation behaviors [2]. Best outcome may be obtained if the agent is able to adjust its strategy, predict or guess the strategy of the other agent [3], or choose an adequate strategy, according to the negotiating partner. Different approaches have been proposed, including machine learning approaches, which can be used to change the agent strategy during negotiation, in order to obtain better results and increased payoffs [4].In our previous works regarding the automated negotiation process, we have proposed bargaining strategies that are based on agent profiles, which can describe statically or can develop dynamically the agent preferences for certain attributes of the negotiation object [5,6]. Using these profiles, agents obtain better results than in the case when fixed negotiation strategies are employed. This paper extends our previous work and proposes an agent model, in which the agents apply the negotiation strategy best suited to them, according to the negotiation situation. A multi-agent environment for automated negotiation is designed, offering services for a real estate business model. In the multi-agent system, there are buyer and seller agents and also a facilitator, which is used when a new agent enters into the system, for registering its services. The agents are designed according to the BDI (Belief-Desire-Intention) model [7]. Each agent has a set of goals, selected from the set of desires.Several use cases scenarios evaluate the negotiation performances. The bargaining takes place in several rounds, before an agreement or a rejection is concluded. In each negotiation round, based on the values and preferences specified by the buyer for the multiple attributes of the negotiation object, the seller agent makes the best possible offer. The agents use linear and non-linear negotiation strategies, which help them in time to increase the gain.The paper is organized as follows: Section 2 presents the negotiation environment, that is our proposed framework for the negotiation system in an open environment. The agent behavior and how each agent acts during the negotiation process is described in Section 3. In Section 4 is applied the develo...

show abstract

“…In this context, many different aspects of negotiation strategies have been studied, ranging from the introduction and evaluation of opponent models [19,28,39,47,63,64] to encounter-based learning approaches [40,59]. Negotiation strategies based on game theoretic approaches are often used for practical applications; however, they have been critiqued in situations where one cannot have complete information about the negotiating environment and the negotiation opponents [31,50].…”

Section: Introductionmentioning

confidence: 99%

Concurrent bilateral negotiation for open e-markets: the Conan strategy

2017

View full text Add to dashboard Cite

We develop a novel strategy that supports software agents to make decisions on how to negotiate for a resource in open and dynamic e-markets. Although existing negotiation strategies offer a number of sophisticated features, including modelling an opponent and negotiating with many opponents simultaneously, they abstract away from the dynamicity of the market and the model that the agent holds for itself in terms of ongoing negotiations, thus ignoring information that increases an agent's utility. Our proposed strategy COncurrent Negotiating AgeNts (Conan) considers a weighted combination of modelling the market environment and the progress of concurrent negotiations in which the agent partakes. We conduct extensive experiments to evaluate the strategy's performance in various settings where different opponents from the literature provide a competitive market. Our experiments provide statistically significant results showing how Conan outperforms the state-of-the-art in terms of the utility gained during negotiations.

show abstract

The Benefits of Opponent Models in Negotiation

Cited by 23 publications

References 11 publications

From problems to protocols: Towards a negotiation handbook

From problems to protocols: Towards a negotiation handbook

Bargain strategies for agent automated negotiation in an e-business environment

Concurrent bilateral negotiation for open e-markets: the Conan strategy

Contact Info

Product

Resources

About