The efficiency of automated multi-issue negotiation depends on the availability and quality of knowledge about an opponent. We present a generic framework based on Bayesian learning to learn an opponent model, i.e. the issue preferences as well as the issue priorities of an opponent. The algorithm proposed is able to effectively learn opponent preferences from bid exchanges by making some assumptions about the preference structure and rationality of the bidding process. The assumptions used are general and consist among others of assumptions about the independency of issue preferences and the topology of functions that are used to model such preferences. Additionally, a rationality assumption is introduced that assumes that agents use a concession-based strategy. It thus extends and generalizes previous work on learning in negotiation by introducing a technique to learn an opponent model for multi-issue negotiations. We present experimental results demonstrating the effectiveness of our approach and discuss an approximation algorithm to ensure scalability of the learning algorithm.

This paper presents a model for integrative, one-to-one negotiation in which the values across multiple attributes are negotiated simultaneously. We model a mechanism in which agents are able to use any amount of incomplete preference information revealed by the negotiation partner in order to improve the efficiency of the reached agreements. Moreover, we show that the outcome of such a negotiation can be further improved by incorporating a "guessing" heuristic, by which an agent uses the history of the opponent's bids to predict his preferences. Experimental evaluation shows that the combination of these two strategies leads to agreement points close to or on the Pareto-efficient frontier. The main original contribution of this paper is that it shows that it is possible for parties in a cooperative negotiation to reveal only a limited amount of preference information to each other, but still obtain significant joint gains in the outcome.

The purpose of this paper is to report on experiments in (human) multi-issue negotiation and their analysis, and to present a generic software environment supporting such an analysis. First, the paper presents a System for Analysis of Multi-Issue Negotiation (SAMIN). SAMIN is designed to analyse negotiation processes between human negotiators, between human and software agents, and between software agents. The user can enter any formal property deemed useful into the system and use the system to automatically check this property in given negotiation traces. Second, the paper presents the results of applying SAMIN in the analysis of empirical traces obtained from an experiment in multi-issue negotiation about second hand cars. In the experiment the efforts of 74 humans negotiating against each other have been analysed using SAMIN. 1.

This paper presents two experiments that contribute to the comparison of human- versus computer behaviour in the domain of multi-issue negotiation. The experiments are part of an ongoing endeavour of improving the quality of computer negotiators when negotiating against human negotiators. The validity of the experiments was tested in a case study of closed multi-issue negotiation involving the ABMP negotiation software agents. The results indeed reveal a number of strengths and weaknesses of the ABMP agents. For example, the fairness of deals in negotiations performed purely by ABMP agents is better than the fairness of deals in the comparable negotiations in which humans were involved. Furthermore, in mixed negotiations (i.e., involving human- and software agents) the humans outperform the software agent with respect to the individual performance. Based on the results of the experiments, several suggestions are made to improve the ABMP agent’s performance. 1.

Negotiation surrounds our day-to-day lives. Research in the field of automated negotiations has suggested the design and use of automated negotiators, on one hand to allow facilitation of the negotiation process by human negotiators and, on the other hand to provide automated agents that can negotiate on behalf of humans. Many papers present innovative agents and evaluate their efficacy in negotiations with other automated agents or people. Others focus on building negotiation support systems with the purpose of helping negotiators reach an agreement. Yet, the question still remains whether these systems or agents have the potential of improving people’s negotiation skills. In this paper we attempt to shed more light on this topic. By means of extensive simulations with human negotiators we examine and compare several training methods and their implications on the improvement of negotiation skills of human negotiators.

Given that a negotiation outcome is determined to a large extent by the successive offers exchanged by negotiating agents, it is useful to analyze dynamic patterns of the bidding, what Raiffa calls the “negotiation dance”. Patterns in such exchanges may provide additional insight into the strategies used by the agents. The current practice of evaluating a negotiation strategy, however, is to primarily focus on fairness and quality aspects of the agreement. There is a lack of tools and methods that facilitate a precise analysis of the negotiation dynamics. To fill this gap, this paper introduces a method for analysis based on a classification of negotiation steps. The method provides the basic tools to perform a detailed and quantified analysis of a negotiation between two agents in terms of dynamic properties of the negotiation trace. The method can be applied to well-designed tournaments, but can also be used to analyze single 1-on-1 negotiation. Example findings of applying the method to analyze the ABMP and Trade-Off strategies show that sensitivity to the preferences of the opponent is independent, respectively dependent, on a correct model of that opponent. Furthermore, the results illustrate that having domain knowledge is not always enough to avoid making unintentional steps. 1.

Abstract. This paper presents the design of an open architecture for heterogeneous negotiating agents. Both the system level architecture as well as the architecture for negotiating agents are provided. The main contribution of this paper is that it derives a precisely specified interface from these architectures that facilitates an easy integration of heterogeneous agents into the overall negotiation framework. The interface is defined as a set of adapters that allows for various levels of integration of agents into the system architecture. The functionality provided by the system architecture depends on the number of adapters that are implemented and used to connect an agent to this architecture, ranging from functionality to conduct a bilateral negotiation to functionality for computing agent internal performance measures such as the quality of an opponent model. The architecture is used as the basis of a competitive testbed which allows us to study various negotiating agents. The design yields a flexible negotiation framework that facilitates negotiating different domains potentially using different protocols whereas no details of the internal negotiating agent structure are enforced. An application of the framework is illustrated by integrating two agents from the literature. 1

Emerging technologies allowing two-way communication between utility companies and their customers are changing the rules of the energy market. Deregulation makes it even more demanding for utility companies to create new business processes for the mutual benefit of the companies and their customers. Dynamic load management of the power grid is essential to make better and more cost-effective use of electricity production capabilities, and to increase customer satisfaction. In this paper, methods from Agent Technology and Knowledge Technology have been used to analyse, design, and implement a component-based multi-agent system capable of negotiation for load management. The proof-of-concept prototype system NALM (Negotiating Agents for Load Management) developed shows how under certain assumptions peaks in power load can be reduced effectively based on a negotiation process.

Computer systems increasingly carry out tasks in mixed networks, that is in group settings in which they interact both with other computer systems and with people. Participants in these heterogeneous human-computer groups vary in their capabilities, goals, and strategies; they may cooperate, collaborate, or compete. The presence of people in mixed networks raises challenges for the design and the evaluation of decision-making strategies for computer agents. This paper describes several new decision-making models that represent, learn and adapt to various social attributes that influence people’s decision-making and presents a novel approach to evaluating such models. It identifies a range of social attributes in an open-network setting that influence people’s decision-making and thus affect the performance of computeragent strategies, and establishes the importance of learning and adaptation to the success of such strategies. The settings vary in the capabilities, goals, and strategies that people bring into their interactions. The studies deploy a configurable system called Colored Trails (CT) that generates a family of games. CT is an abstract, conceptually simple but highly versatile game in which players negotiate and exchange resources to enable them to achieve their individual or group goals. It provides a realistic analogue to multi-agent task than payoff matrices, and people exhibit less strategic and more helpful behavior in CT than in the identical payoff matrix decision-making context. By not requiring extensive domain modeling, CT enables agent researchers to focus their attention on strategy design, and it provides an environment in which the influence of social factors can be better isolated and studied.

Abstract. The process of reaching an agreement in a bilateral negotiation to a large extent determines that agreement. The tactics of proposing an offer and the perception of offers made by the other party determine how both parties engage each other and, as a consequence, the kind of agreement they will establish. It thus is important to gain a better understanding of the tactics and potential other factors that play a role in shaping that process. A negotiation, however, is typically judged by the efficiency of the outcome. The process of reaching an outcome has received less attention in literature and the analysis of the negotiation process is typically not as rigorous nor is it based on formal tools. Here we present an outline of a formal toolbox to analyze and study the dynamics of negotiation based on an analysis of the types of moves parties to a negotiation can make while exchanging offers. This toolbox can be used to study both the performance of human negotiators as well as automated negotiation systems. 1