What to Bid and When to Stop

Every year, automated negotiation agents are improving on various domains. However, given a set of negotiation agents, current methods allow to determine which strategy is best in terms of utility, but not so much the reason of success. In order to study the performance of the individual elements of a negotiation strategy, we introduce an architecture that distinguishes three components which together constitute a negotiation strategy: the bidding strategy, the opponent model, and the acceptance condition. Our contribution to the field of bilateral negotiation is threefold: first, we show that existing state of the art agents are compatible with this architecture; second, as an application of our architecture, we systematically explore the space of possible strategies by recombining different strategy components; finally, we briefly review how the BOA architecture has been recently applied to evaluate the performance of strategy components and create novel negotiation strategies that outperform the state of the art.

Determining an effective strategy for intelligent agents in multilateral negotiations is a more complicated problem than in bilateral negotiations. In order to achieve an optimal and beneficial agreement the agent needs to consider the behavior and desired utility of more than one opponent, determine a concession tactic based on a smaller agreement space, and use a computationally efficient mechanism for generating optimal offers. However, a mere extension of bilateral negotiation strategies cannot be effective in multilateral negotiations because the nature of most bilateral negotiation strategies is based on interaction with only one opponent and tracking a single behavior during the negotiation process. In this paper, we propose an adaptive approach based on a multi-party perspective to determine multilateral negotiation strategy. The proposed approach applies the BOA framework (Bidding, Opponent model, and Acceptance) and dynamically models the opponents’ preference profiles. In order to estimate the obtainable utility from opponents and help find a good offer, the agent uses an ensemble model made by individual frequency-based opponent models and a different level of attention to each party’s behavior. The proposed approach also implements a bidding strategy which applies the opponents’ desirable utility to adapt the agent’s concession tactic and produce appropriate offers. The results of experimental evaluations on various negotiation scenarios against the state of the art multilateral negotiation strategies show that our proposed strategy can provide superior performance in both individual utility and social welfare and lead to more optimal and fairer agreements.

An efficient and robust negotiating strategy in bilateral negotiations over multiple items

Designing negotiator agents who adopt real-world inspired negotiation strategies in front of different types of negotiation scenario increases the chance of having better utility and success rate in negotiation-based cloud resource allocation. To realize real-world inspired multi-strategy based negotiating system for cloud marketplace, three following issues are focused in this paper: 1) Designing a new negotiation_strategy_basket with the aim of approaching the strategies of the real-world negotiation markets, 2) Modeling the critical condition of the cloud trading market, and 3) Adopting a new fuzzy decision system (i.e., Fuzzy Negotiation Strategy Selection System (FNSSDS)) for conducting negotiator agents of type resource providers and resource customers in how to select a suitable negotiation strategy from negotiation_strategy_basket according to the critical condition of the cloud trading market. We perform extensive simulation experiments to compare the performance of the proposed negotiator agents with the well known negotiator agents in name MDA (Market Driven Agent). The results show that the proposed negotiation agents outperform the MDAs.

Several types of researches have been carried out prior to the new millennium on the subject of bidding strategies in the construction industry. Today, organizations are faced with a very complex decision of bid/no-bid because it requires the assessment of large number of highly inter-related variables. The study aims at examining different types of Contractors’ Bidding Strategies (CBS) with a view to determining their impact on bid success. In line with the aim, the study objectives include; evaluation of different types of CBS and; assessment of the success rate of contractors’ bid. The method of approach elicits information on the number of projects bided and successes recorded over a period of time. A total of one hundred and seventy-one useable responses were retrieved from questionnaire administration. Descriptive statistics, tables and percentages as well as mean item score (MIS) were used for data analysis. The study showed that lowest bid, public relations and joint venture bidding strategies have great impact on contractors’ bid success especially on residential, educational and administrative projects in the Nigeria Construction Industry (NCI). Therefore, the study concluded that relationship exists between contractors’ bidding strategies and equivalent successes recorded over a period of time. It is important to also know that lowest bid strategy still remains the most effective bidding strategy for public works contracting in the NCI.

Opponent modeling is an important technique in automated negotiations. Many of the existing opponent modeling methods are focusing on predicting the opponent’s private information to improve the agent’s benefits. However, these modeling methods overlook an ability to improve the negotiation outcomes by adapting to different types of private information about the opponent when they are available beforehand. This availability may be provided by some prediction algorithms, or be prior knowledge of the agent. In this paper, we name the above ability as Information Adaptation, and propose a novel Opponent Modeling method with Information Adaptation (OMIA). Specifically, the future concessions of the opponent will firstly be learned based on the opponent’s historical offers. Then, an expected utility calculation function is introduced to adaptively guide the agent’s negotiation strategy by considering the availability and value of the opponent’s private information. The experimental results show that OMIA can adapt to different types of information, helping the agent reach agreements with the opponent and achieve higher utility values comparing to those which lack the information adaptation ability.

In every negotiation with a deadline, one of the negotiating parties has to accept an offer to avoid a break off. A break off is usually an undesirable outcome for both parties, therefore it is important that a negotiator employs a proficient mechanism to decide under which conditions to accept. When designing such conditions one is faced with the acceptance dilemma: accepting the current offer may be suboptimal, as better offers may still be presented. On the other hand, accepting too late may prevent an agreement from being reached, resulting in a break off with no gain for either party. Motivated by the challenges of bilateral negotiations between automated agents and by the results and insights of the automated negotiating agents competition (ANAC), we classify and compare state-of-the-art generic acceptance conditions. We focus on decoupled acceptance conditions, i.e. conditions that do not depend on the bidding strategy that is used. We performed extensive experiments to compare the performance of acceptance conditions in combination with a broad range of bidding strategies and negotiation domains. Furthermore we propose new acceptance conditions and we demonstrate that they outperform the other conditions that we study. In particular, it is shown that they outperform the standard acceptance condition of comparing the current offer with the offer the agent is ready to send out. We also provide insight in to why some conditions work better than others and investigate correlations between the properties of the negotiation environment and the efficacy of acceptance conditions.

Fox a multi-agent electronic negotiating environment to be successful, intelligent agents should be capable of adapting their negotiation strategies and tactics to achieve an agreement with optimized profit. This paper aims to present some findings from which negotiating intelligent agents in electronic commerce start negotiating using a simplified standard protocol in conjunction with a combined negotiation. Taking advantage of a new developed evolutionary algorithm, agents configure their negotiation strategies somehow they can get more profit. They can use fuzzy fairness function to have behavior with fairness or without fairness.

The burgeoning landscape of e-commerce has transformed traditional marketplaces, giving rise to complex, dynamic environments where automated negotiation agents can play a pivotal role. Effective autonomous negotiation requires agents to not only understand their own objectives but also to strategically interact with and adapt to the behaviors of other participants. This article provides a comprehensive review of the synergistic integration of reinforcement learning (RL) and game theory (GT) to develop intelligent bargaining agents for digital marketplaces. We delve into how RL enables agents to learn optimal negotiation strategies through experience, even in environments with imperfect information and unknown opponents, while GT provides the theoretical foundation for rational decision-making, equilibrium analysis, and strategic interactions. By synthesizing empirical findings from various applications, including multi-issue bargaining and team formation, we illustrate the distinct advantages of combining these paradigms over purely isolated approaches. Furthermore, we address the current limitations of such hybrid frameworks and outline critical future research directions towards building more robust, adaptive, and human-like negotiation agents in e-commerce.

In argumentation-based negotiation based on multi-agent, if a negotiator agent is endowed with ability of self-learning, then it can acquire much more information about opponent's costs and benefits to achieve the purpose of improving negotiated efficiency. This paper discusses the problem of adaptive strategy in intelligent argumentation-based negotiation, presents a generating process of adaptive strategy, optimizes and improves the process by using a method of machine learning to help negotiator to determine valid candidate concessional attributes and concessional values. Finally, this paper also describes an implementing process of the strategy model and explains it in details. The research results of this paper provide new ideas and measures for solving the problem that how to generate reasonable adaptive strategies in argumentation-based negotiation.

This work investigates the problem of finding near-optimal strategies for the bilateral negotiation with incomplete information between two competitive negotiation agents for resolving the differences in their objectives and preferences. While there are some former studies of finding negotiation strategies using evolutionary approaches, there are extremely few works on effectively locating the global optimal solution. In this study, we use a genetic algorithm (GA) to find near-optimal negotiation strategies for both negotiation agents conducting bilateral negotiation by coevolving both agents' strategies. Agents learn optimal strategies through trial-and-error, which is done by matching and negotiation of agents of one population with agents of the other population through random pairing in a one-to-one manner. However, a simple GA often cannot find the optimum results for both agents for the following reasons: (i) the premature convergence of a simple GA in itself, and (ii) both parties' failure to keep pace with each other's learning speed in the coevolution. To solve this problem, this paper proposes a GA which has a novel dynamic diversity controlling capability. The proposed method utilizes the accumulated frequency information of the occurrence of individuals in each band of the population for generations. The information is used in a diversification and refinement procedure of the proposed diversity controlling GA. Empirical results show that the proposed dynamic diversity controlling GA generally outperforms the traditional GA for finding near-optimal negotiation strategies.

The human's ability for taking risk, which is one of the most important human attributes, has strong effect on his decision making. The bidding problem is an important issue for supplier agent participating in the power market. Thus, in order to get realistic insight about the supplier behavior, it is necessary to model the supplier's risk strategy and evaluate its effect on the bidding problem. Considering the human's thinking fuzzy nature, the supplier agent's risk characteristic is modeled using the fuzzy logic. Combining the fuzzy logic with the Q-learning algorithm, the intelligent supplier agent' bidding strategy is determined based on his risk strategy. A simulator is designed based on the proposed method. The supplier agents' realistic behaviors with different characteristics are studied numerically using the designed simulator

A complex and challenging bilateral negotiation environment for rational autonomous agents is where agents negotiate multi-issue contracts in unknown application domains against unknown opponents under real-time constraints. In this paper we present a novel negotiation strategy called EMAR for this kind of environment which is based on a combination of Empirical Mode Decomposition (EMD) and Autoregressive Moving Average (ARMA). EMAR enables a negotiating agent to adjust its target utility and concession rate adaptively in real-time according to the behavior of its opponent. The experimental results show that this new strategy outperforms the best agents from the latest Automated Negotiation Agents (ANAC) Competition in a wide range of application domains.

Prediction of partners' behaviors in negotiation has been an active research direction in recent years in the area of multi-agent and agent system. So by employing the prediction results, agents can modify their own negotiation strategies in order to achieve an agreement much quicker or to look after much higher benefits. Even though some of prediction strategies have been proposed by researchers, most of them are based on machine learning mechanisms which require a training process in advance. However, in most circumstances, the machine learning approaches might not work well for some kinds of agents whose behaviors are excluded in the training data. In order to address this issue, we propose three regression functions to predict agents' behaviors in this paper, which are linear, power and quadratic regression functions. The experimental results illustrate that the proposed functions can estimate partners' potential behaviors successfully and efficiently in different circumstances.

Automated negotiation among self-interested autonomous agents has gained tremendous attention due to the diversity of its broad range of potential real-world applications. This article deals with a prominent type of such negotiations, namely, multiissue negotiation that runs under continuous-time constraints and in which the negotiating agents have no prior knowledge about their opponents’ preferences and strategies. A negotiation strategy called Dragon is described that employs sparse pseudoinput Gaussian processes. Specifically, Dragon enables an agent (1) to precisely model the behavior of its opponents with comparably low computational load and (2) to make decisions effectively and adaptively in very complex negotiation settings. Extensive experimental results, based on a number of negotiation scenarios and state-of-the-art negotiating agents from Automated Negotiating Agents Competitions, are provided. Moreover, the robustness of our strategy is evaluated through both empirical game-theoretic and spatial evolutionary game-theoretic analysis.