Agent-based Negotiation Research Articles

Emotion-driven reasoning model for agent-based human–computer negotiation

Human-computer negotiation plays an important role in today's highly developed online transactions. Agents need to have higher emotional intelligence to deal with the random actions of human adversaries. Most of the existing studies focus on deterministic modeling but neglect the role of fuzziness in human–computer negotiation and emotion effects on the interaction between persuasion strategy selection and issue updating. This paper uses emotional rendering to describe the emotional interaction between agents to supplement the emotion generation process in agent-based negotiation. Moreover, this paper constructs emotion-driven reasoning model which integrates an agent’s assessment of emotion and actual utility, and proposes a mechanism for the selection of persuasion strategies and negotiating issue updating driven by the agent’s reasoning ability. A series of agent-agent experiments are conducted, and a human–computer negotiation system is developed for the real human-agent experiment. The agent-agent experimental results show that, compared with the non-emotion model, the proposed model increases the joint utility by 55.1% and compared with the non-reasoning model, the proposed model improves the success rate by 49.2%. Meanwhile, the proposed model is superior to several existing competing models in terms of the success rate, the negotiating rounds, and the success utility. The human-agent experimental results show that the developed negotiation system can achieve satisfactory results with human opponents.

A Q-learning approach to generating behavior of emotional persuasion with adaptive time belief in decision-making of agent-based negotiation

There is an increasing research interest in agent-based automated negotiation. However, how to design an agent that can adaptively compete with its human counterpart is still in its early stage. This research makes efforts toward this end by modeling two essential elements of human-led negotiation: emotion and timing, to adapt to negotiation dynamics. In multi-issue-multi-round bilateral negotiation, the Web-Fechner law is applied to model an agent’s emotion generation and the emotion decay law is used to realize a decaying property of emotion. Meanwhile, rather than a fixed time belief, agents are endowed with time beliefs that can vary with selected negotiation tactics and be adjusted by agents’ emotions. A proposal updating algorithm integrating those two elements is consequently proposed based on Q-learning. Then, 135 numerical experiments were conducted with comparative analyses and statistical tests. The results show that the proposed model can significantly increase an individual agent’s utility, the joint utility, and the probability of successful negotiations by an average of 76.14%, 172.22%, and 66.10%, respectively, whereas reducing the utility difference and negotiation rounds by an average of 97.39% and 29.57%, respectively. These results imply that the proposed negotiation model has advantages in improving negotiation utility, efficiency, and outcome fairness.

Agent-Based Personalized Assessment Tasks Recommendation Considering Objective and Subjective Factors

In traditional education, there is not much difference between assessment tasks designed for learners. However, learners’ learning performance may vary due to a number of factors, e.g., learning ability, academic emotion, and learners’ and teachers’ academic expectations. Considering those factors, accurately recommending personalized assessment tasks for each learner is challenging. To overcome the limitations in the current work, this paper proposed an autonomous-agent-based approach to recommend personalized assessment tasks considering multiple factors. Contributions of the proposed approach contain three aspects: (1) Considering objective factors, the proposed approach dynamically adjusts the assessment tasks recommended for students. (2) Considering subjective factors, the proposed approach can dynamically predict learners’ learning performances by applying autonomous agent-based negotiation. (3) The proposed recommendation algorithm can handle the problems of cold start in the research of typical recommendation algorithms. A set of experiments evaluates the effectiveness of the proposed approach in this paper, and the experimental results show that the proposed approach can accurately and adaptively generate personalized assessment tasks considering objective and subjective factors.

Agent-based Negotiation for Cooperative Transports within Aircraft Production

Multi-agent systems have been used for many decades to solve problems within complex industrial systems. The most common means of coordination is the Contract Net Protocol, a simple yet powerful auction protocol, which has been enhanced by many authors and addressed by different standardization efforts. Autonomous transportation for aircraft production is a particularly challenging area of automation. It necessitates flexible and reliable approaches, including reliable communication and execution of processes for which existing agent frameworks are insufficient. This contribution outlines current efforts within the community to build a ROS2-based agent framework and proposes an applicable capability-modeling approach as well as a suitable negotiation protocol for cooperative transport processes.

Automated privacy negotiations with preference uncertainty

Many service providers require permissions to access privacy-sensitive data that are not necessary for their core functionality. To support users’ privacy management, we propose a novel agent-based negotiation framework to negotiate privacy permissions between users and service providers using a new multi-issue alternating-offer protocol based on exchanges of partial and complete offers. Additionally, we introduce a novel approach to learning users’ preferences in negotiation and present two variants of this approach: one variant personalised to each individual user, and one personalised depending on the user’s privacy type. To evaluate them, we perform a user study with participants, using an experimental tool installed on the participants’ mobile devices. We compare the take-it-or-leave-it approach, in which users are required to accept all permissions requested by a service, to negotiation, which respects their preferences. Our results show that users share personal data 2.5 times more often when they are able to negotiate while maintaining the same level of decision regret. Moreover, negotiation can be less mentally demanding than the take-it-or-leave-it approach and it allows users to align their privacy choices with their preferences. Finally, our findings provide insight into users’ data sharing strategies to guide the future of automated and negotiable privacy management mechanisms.

Fuzzy constraint-based agent negotiation framework for doctor-patient shared decision-making

BackgroundThe clinical practice of shared decision-making (SDM) has grown in importance. However, most studies on SDM practice concentrated on providing auxiliary knowledge from the third-party standpoint without consideration for the value preferences of doctors and patients. The essences of these methods are complete and manual negotiation, and the problems of high cost, time consumption, delayed response, and decision fatigue are serious.MethodsIn response to the above limitations, this article proposes a fuzzy constraint-directed agent-based negotiation and recommendation framework for bilateral and multi-issue preference negotiation in SDM (PN-SDM). Its purpose is to provide preference information and intellectualize PN-SDM to promote SDM practice. We modeled PN-SDM problems as distributed fuzzy constraint satisfaction problems and designed the doctor agent and patient agent to negotiate on behalf of the doctor and patient. The negotiation result was then transformed into treatment plans by the recommendation model. The proposed negotiation and recommendation models were introduced in detail by an instance.ResultsThe proposed method with different strategies and negotiation pairs achieves good performance in terms of negotiation running time, negotiation rounds, and combined aggregated satisfaction value. Specifically, it can feasibly and effectively complete multiple rounds of PN-SDM in a few seconds and obtain higher satisfaction.ConclusionThe experimental results indicate that the negotiation model can effectively simulate preference negotiation and relieve the pressure of increasing issues. The recommendation model can assist in decision-making and help to realize SDM. In addition, it can flexibly cope with various negotiation scenarios by using different negotiation strategies (e.g., collaborative, win–win, and competitive).

An agent-based negotiation protocol for supply chain finance

Supply chain finance (SCF) makes it possible to discover and utilize optimization potentials concerning the financial flows of a supply chain. A key feature of SCF is the provision of financial support based on a core business that extends good credit to upstream and downstream businesses and facilitates lending without taking unacceptable risks. To this end, a multi-agent system (MAS) approach is proposed to automate and facilitate the process of selecting the best possible financing options in the supply chain. It must be decided whether internal or external financing is to be used and which internal player offers the most favourable financing option. This second decision-making problem is realized in the MAS by an automated negotiation process in the form of an auction. The model considers the information asymmetry between external and internal supply chain actors and additional external effects for internal supply chain actors while taking over financing. Numerical experiments show the functionality and advantages of the specially designed negotiation protocol.

An autonomous agent for negotiation with multiple communication channels using parametrized deep Q-network

<abstract><p>Agent-based negotiation aims at automating the negotiation process on behalf of humans to save time and effort. While successful, the current research considers communication between negotiation agents through offer exchange. In addition to the simple manner, many real-world settings tend to involve linguistic channels with which negotiators can express intentions, ask questions, and discuss plans. The information bandwidth of traditional negotiation is therefore restricted and grounded in the action space. Against this background, a negotiation agent called MCAN (multiple channel automated negotiation) is described that models the negotiation with multiple communication channels problem as a Markov decision problem with a hybrid action space. The agent employs a novel deep reinforcement learning technique to generate an efficient strategy, which can interact with different opponents, i.e., other negotiation agents or human players. Specifically, the agent leverages parametrized deep Q-networks (P-DQNs) that provides solutions for a hybrid discrete-continuous action space, thereby learning a comprehensive negotiation strategy that integrates linguistic communication skills and bidding strategies. The extensive experimental results show that the MCAN agent outperforms other agents as well as human players in terms of averaged utility. A high human perception evaluation is also reported based on a user study. Moreover, a comparative experiment shows how the P-DQNs algorithm promotes the performance of the MCAN agent.</p></abstract>

Nova : Value-based Negotiation of Norms

Specifying a normative multiagent system (nMAS) is challenging, because different agents often have conflicting requirements. Whereas existing approaches can resolve clear-cut conflicts, tradeoffs might occur in practice among alternative nMAS specifications with no apparent resolution. To produce an nMAS specification that is acceptable to each agent, we model the specification process as a negotiation over a set of norms. We propose an agent-based negotiation framework, where agents’ requirements are represented as values (e.g., patient safety, privacy, and national security), and an agent revises the nMAS specification to promote its values by executing a set of norm revision rules that incorporate ontology-based reasoning. To demonstrate that our framework supports creating a transparent and accountable nMAS specification, we conduct an experiment with human participants who negotiate against our agent. Our findings show that our negotiation agent reaches better agreements (with small p -value and large effect size) faster than a baseline strategy. Moreover, participants perceive that our agent enables more collaborative and transparent negotiations than the baseline (with small p -value and large effect size in particular settings) toward reaching an agreement.

Brokered pricing model for agent-based negotiation of data-driven services in the cloud

Brokered pricing model for agent-based negotiation of data-driven services in the cloud

An agent-based negotiation scheme for the distribution of electric vehicles across a set of charging stations

We consider the problem of scheduling Electric Vehicle (EV) charging within a set of multiple charging stations. Each station aims to maximize the amount of charged energy and the number of charged EVs. We propose an agent-based simulation scheme, where the EVs announce their requests to the stations and each station computes an optimal solution using Integer Linear Programming (ILP) techniques. We propose two variations of the problem, namely the Offline Mode and the Online Mode. In the first one, all the EVs send their charging requests simultaneously at the beginning of the simulation and the stations compute their charging schedules at once, while in the second one each EV may send a charging request at whichever time point and the stations compute their charging schedules incrementally. Moreover, we apply agent-based negotiation techniques between the stations and the EVs to service EVs when the ILP problem is initially unsolvable due to insufficient resources at some stations. Finally, we insert delays in the Online Mode, meaning that an EV that came to an agreement with a station may cancel this agreement and request charging anew. We test our scheme for both variations, Offline and Online, for a diverse set of stations and EVs and show the outcomes of the different scenarios in the system.

Efficient agent-based negotiation by predicting opponent preferences using AHP

Negotiation is a process essential for a wide range of applications. The complex decision making involved in negotiation makes its automation difficult. The complexity is further increased as negotiators hide their individual preferences from each other to avoid exploitation by the opponent. Even though sharing of private preference information leads to better agreement for both sides, it is never done in the absence of trust. In this work, we learn opponent’s preference information from the offers given by the opponent using Analytic Hierarchy Process (AHP). We apply our approach to the negotiation of Quality-of-Service (QoS) parameters for the establishment of Service Level Agreements (SLA) between a provider and a consumer. Experiments show that using AHP, the negotiations are faster and the agreements are on or nearer to the pareto-optimal line.

Efficient agent-based negotiation by predicting opponent preferences using AHP

Negotiation is a process essential for a wide range of applications. The complex decision making involved in negotiation makes its automation difficult. The complexity is further increased as negotiators hide their individual preferences from each other to avoid exploitation by the opponent. Even though sharing of private preference information leads to better agreement for both sides, it is never done in the absence of trust. In this work, we learn opponent’s preference information from the offers given by the opponent using Analytic Hierarchy Process (AHP). We apply our approach to the negotiation of Quality-of-Service (QoS) parameters for the establishment of Service Level Agreements (SLA) between a provider and a consumer. Experiments show that using AHP, the negotiations are faster and the agreements are on or nearer to the pareto-optimal line.

Simulation model study for manufacturing effectiveness evaluation in crowdsourced manufacturing

Crowdsourced manufacturing, a new type of manufacturing in which companies share their manufacturing resources depending on their demand and capacity, is discussed in one of the main ideas of Industry 4.0 concept. According to this, companies share their resource information and can find an outsourcing company when they need specific or extra resources. In this study, we have developed a simulation model of crowdsourced manufacturing with a resource model and an agent-based negotiation algorithm to evaluate manufacturing effectiveness based on delivery and machine usage. According to a combination and balance of business style, the delivery rate changes with the saturation point which depends on resource commonality.

An Agent-Based Bilateral Negotiation Model About Price and Quantity Considering Nonlinear Utility

An Agent-Based Bilateral Negotiation Model About Price and Quantity Considering Nonlinear Utility

A hybrid multi-agent negotiation protocol supporting supplier selection for multiple products with synergy effect

Supplier selection is an important problem in supply chain management. In practice, it is common for a purchasing company to procure a bundle of products simultaneously. In this regard, synergy effect could exist between products and hence affect the final choice of suppliers. It is therefore necessary to incorporate the synergy effect between products in supplier selection process. Agent-based negotiation models are applied to automate supplier selection process. Negotiation protocol is an essential component should be considered when building an effective agent negotiation model. The objective of this research is to propose a negotiation protocol special for multi-product supplier selection problem. The negotiation protocol is a hybrid multi-agent protocol of combinatorial procurement auction protocol and multi-bilateral bargaining protocol. The negotiation protocol is able to support the purchasing company and suppliers negotiate on the concrete commitments of multiple products simultaneously, and select suppliers for multiple products. In addition, both the purchasing company and suppliers can express their preferences on the synergy effect between products in negotiation process by adopting the negotiation protocol. Simulation is conducted to demonstrate the effectiveness and efficiency of the negotiation protocol.

A win–win team formation problem based on the negotiation

Nowadays, many researches focus on the selection of the team members, and aim to form a team that can solve a common task collaboratively or achieve a certain goal cooperatively. The leader or manager needs to maximize the benefit of the team by selecting the appropriate team members from the available candidates. However, the personal opinions of team members have not been considered in the team formation process. In this paper, in order to consider the mutual decision between the leader and the team members, a negotiation based team formation problem is defined firstly, in which the balance of the benefit requirements of the leader and the team members is addressed. Then, a negotiation model between the leader and the team members is proposed to implement the team formation process. According to the conflicts in the process, an incentive mechanism based on the payoff is adopted. Finally, the agent-based negotiation approach is introduced to construct the simulation environment of the negotiation. The negotiation process is iterated until the benefit requirements of the leader agent and the candidate agents are all satisfied or the deadline of the negotiation is reached. The experiment results indicate that the team can be formed successfully in different team contexts, such as different team sizes, different minimum criteria of team positions and different incentive levels. Comparing with the leader׳s unilateral decision process, the negotiation-based team formation can make the team members acquire more benefits. In addition, the different preferences of the candidates have different effects on the final benefit acquirements, and the different minimum criteria of team positions and incentive levels have different effects on the conflicts resolution.

An approach to complex agent-based negotiations via effectively modeling unknown opponents

Negotiation among computational autonomous agents has gained rapidly growing interest in previous years, mainly due to its broad application potential in many areas such as e-commerce and e-business. This work deals with automated bilateral multi-issue negotiation in complex environments. Although tremendous progress has been made, available algorithms and techniques typically are limited in their applicability for more complex situations, in that most of them are based on simplifying assumptions about the negotiation complexity such as simple or partially known opponent behaviors and availability of negotiation history. We propose a negotiation approach called OMAC★ that aims at tackling these problems. OMAC★ enables an agent to efficiently model opponents in real-time through discrete wavelet transformation and non-linear regression with Gaussian processes. Based on the approximated model the decision-making component of OMAC★ adaptively adjusts its utility expectations and negotiation moves. Extensive experimental results are provided that demonstrate the negotiation qualities of OMAC★, both from the standard mean-score performance perspective and the perspective of empirical game theory. The results show that OMAC★ outperforms the top agents from the 2012, 2011 and 2010 International Automated Negotiating Agents Competition (ANAC) in a broad range of negotiation scenarios.

An agent-based negotiation model for supplier selection of multiple products with synergy effect

Supplier selection is an important problem in supply chain management (SCM), and has attracted the attention of many researchers. Tremendous effort has been spent on the development of agent-based systems to automate supplier selection negotiation process in SCM applications. In this kind of multi-agent system (MAS), software agents are established to represent various parties and functions involving in the supplier selection negotiation process. Most of current systems only deal with relatively simple negotiations involving the acquisition of one product, they are not sufficient to support complex negotiations involving multiple products with synergy effect. However, in practice, it is common for a purchasing company to procure multiple products simultaneously, and the synergy effects that exist between products could affect the final choice of cooperative suppliers. This paper presents an agent-based negotiation model to automate the supplier selection process involving a bundle of products with synergy effect. A MAS is established to realize the proposed negotiation model for multi-product supplier selection. Furthermore, the negotiation proposal, negotiation protocol, negotiation strategies, and decision making methods involving in the negotiation model are elaborated for the multi-product supplier selection environment. Through the proposed negotiation model, the purchasing company and suppliers can reach agreements on the details of products simultaneously and exploit the synergy effect between products. Finally, illustrative examples are conducted to demonstrate the function and effectiveness of the negotiation model for multi-product supplier selection.

A hybrid multi-agent negotiation protocol supporting agent mobility in virtual enterprises

It is a growing trend for supply chain members to collaborate in a virtual enterprise (VE). As VE members are usually geographically dispersed and they have to cooperate and negotiate to achieve mutual agreements, the distributive multi-agent systems (MAS) are being increasingly adopted for VE implementation. To cope with the flexibility requirements of VE, a new MAS architecture is proposed in this paper. In this MAS, the VE initiator can be represented by either stationary or mobile agents to negotiate with VE partners. As there is not a mobile agent-based negotiation scheme considering both the negotiation effectiveness and system security, a hybrid multi-agent negotiation protocol is established in this paper to tackle this problem. This hybrid protocol incorporates both the stationary and mobile agent negotiation phases to compose a more efficient and successful multilateral agent interaction regulation. In this negotiation process, mobile agent-based negotiation is first initiated, it will then switch to stationary agent-based negotiation when mobile agent migration is rejected or interaction is blocked in the remote host. Besides, the ontology-based approach is adopted in the MAS and an embedding ontology operation protocol is established to refine the knowledge expression pattern in the agent negotiation process. The validity and efficiency of the protocol are verified through the execution of a hypothetical VE negotiation case.