Uncertain agency models with multi-dimensional incomplete information based on confidence level

This paper discusses a principal–agent problem with multi-dimensional incomplete information between a principal and an agent. Firstly, how to describe the incomplete information in such agency problem is a challenging issue. This paper characterizes the incomplete information by uncertain variable, because it has been an appropriate tool to depict subjective assessment and model human uncertainty. Secondly, the relevant literature often used expected-utility-maximization to measure the two participators’ goals. However, Ellsberg paradox indicates that expected utility criterion is not always appropriate to be regarded as decision rule. For this reason, this paper presents another decision rule based on confidence level. Instead of expected-utility-maximization, the principal’s aim is to maximize his potential income under the acceptable confidence level, and the agent’s aim depends on whether he has private information about his efforts. According to the agent’s different decision rules, three classes of uncertain agency (UA) models and their respective optimal contracts are presented. Finally, a portfolio selection problem is studied to demonstrate the modeling idea and the viability of the proposed UA models.     

A DEA methodology to evaluate the impact of information asymmetry on the efficiency of not-for-profit organizations with an application to higher education in Brazil

This paper presents a conceptual framework and an analytical DEA model for evaluating the impact of information asymmetry on organizational efficiency. The framework uses concepts from agency theory to estimate the extent of moral hazard by comparing the objectives of the principal to those of the agent. The framework and model are useful in the analysis of both for-profit and not-for-profit organizations because DEA is applicable whether or not inputs and/or outputs are subject to pricing mechanisms. An illustration focusing on the Brazilian not-for-profit federal university system finds that the agency problem indeed exists for a subset of those institutions, indicating the desirability of improved incentive and control mechanisms on the part of the principal.     

Optimal and robust contracts for a risk-constrained principal

The theory of risk measurement has been extensively developed over the past ten years or so, but there has been comparatively little effort devoted to using this theory to inform portfolio choice. One theme of this paper is to study how an investor in a conventional log-Brownian market would invest to optimize expected utility of terminal wealth, when subjected to a bound on his risk, as measured by a coherent law-invariant risk measure. Results of Kusuoka lead to remarkably complete expressions for the solution to this problem. The second theme of the paper is to discuss how one would actually manage (not just measure) risk. We study a principal/agent problem, where the principal is required to satisfy some risk constraint. The principal proposes a compensation package to the agent, who then optimises selfishly ignoring the risk constraint. The principal can pick a compensation package that induces the agent to select the principal’s optimal choice.     

Analysis of various optimal contracts in the problem of stimulation of agents by a principal in a model with two agents

This work is devoted to one section of a game theory popular in recent years, the theory of contracts and the problem of an agent and a principal. A principal tries to stimulate agents into making a number of contracts with clients using his resources in order to maximize his profits as a result. At the same time, the principal has limited information about the agents. He knows only the results he has obtained; he does not know their type or the efforts made. The strategy of the principal is an incentive scheme that shows the agent’s reward depending on his results. In turn, the agents try to maximize their benefits while having the right to turn down a contract. We do not consider models with random events, and we restrict ourselves to the deterministic case. The model thus does not fall under the heading of a moral hazard but is related to a situation of unfavorable selection.     

具有竞争关系的多参与人委托代理问题研究

针对多委托人一多代理人委托代理问题,本文在多委托人之间和多代理人之间均存在竞争关系情形下,建立了非对称信息委托代理模型.分析表明,代理人努力水平对其产出的作用越敏感,代理人和委托人都越愿意付出更多努力;当委托人业务能力高低对代理人的影响较敏感时,委托人更愿意花心思去提高业务能力;委托一代理关系中的任何一方竞争过于激烈时会被处于委托一代理关系中的另一方利用.     

Experimentation and Learning in Repeated Cooperation

We study an agency model, in which the principal has only incomplete information about the agent's preferences, in a dynamic setting. Through repeated interaction with the agent, the principal learns about the agent's preferences and can thus adjust the inventive system. In a dynamic computational model, we compare different learning strategies of the principal when facing different types of agents. The results indicate that better learning of preferences can improve the situation of both parties, but the learning process is rather sensitive to random disturbances.     

Optimal derivatives design for mean–variance agents under adverse selection

We consider a problem of derivatives design under asymmetry of information: the principal sells a contingent claim to an agent, the type of whom he does not know. More precisely, the principal designs a contingent claim and prices it for each possible agent type, in such a way that each agent picks the contingent claim and pays the price that the principal designed for him. We assume that the preferences of the agent depend linearly on the parameters which determine the agent’s type; this model is rich enough to accommodate quadratic utilities. The problem then is reformulated as an optimization problem, where the optimization is performed within a class of convex functions. We prove an existence result for the provide explicit examples in the case when the agent is fully characterized by a single parameter     

The Value of Preference Information in Agency Relationships

Standard models of agency theory often assume that the principal has complete information about the preferences of the agent. This paper starts from the assumption of incomplete information on the agent&2018;s preferences and models a situation where the principal can obtain additional preference information before concluding a contract with the agent. We introduce the concept of a Value of Preference Information (VPI), which describes the benefits to the principal from obtaining such information. This information can be obtained either before or after the principal knows the precise structure of the decision problems which will be delegated to the agent. Analytic and simulation techniques are used to study factors influencing the VPI in these two situations.     

基于代理成本的供应链利润分配研究

针对不对称信息带来的代理成本对供应链利润分配的影响,文章以委托代理理论和合作博弈为基本研究方法,引入虚拟第三方为利他的委托人,研究基于代理成本的供应链利润分配问题。结果表明:为了实现对供应商逆向选择的激励和销售商道德风险的激励,当虚拟第三方提供给供销双方的转移支付之和等于供应链总期望销售收入时,供销双方则得到自身预期的收益,否则,双方需在差额上进一步进行谈判协商,最后结合算例进行了分析论证。     

Effort Games and the Price of Myopia

We consider Effort Games, a game‐theoretic model of cooperation in open environments, which is a variant of the principal‐agent problem from economic theory. In our multiagent domain, a common project depends on various tasks; carrying out certain subsets of the tasks completes the project successfully, while carrying out other subsets does not. The probability of carrying out a task is higher when the agent in charge of it exerts effort, at a certain cost for that agent. A central authority, called the principal, attempts to incentivize agents to exert effort, but can only reward agents based on the success of the entire project. We model this domain as a normal form game, where the payoffs for each strategy profile are defined based on the different probabilities of carrying out each task and on the boolean function that defines which task subsets complete the project, and which do not. We view this boolean function as a simple coalitional game, and call this game the underlying coalitional game. We suggest the Price of Myopia (PoM) as a measure of the influence the model of rationality has on the minimal payments the principal has to make in order to motivate the agents in such a domain to exert effort. We consider the computational complexity of testing whether exerting effort is a dominant strategy for an agent, and of finding a reward strategy for this domain, using either a dominant strategy equilibrium or using iterated elimination of dominated strategies. We show these problems are generally #P‐hard, and that they are at least as computationally hard as calculating the Banzhaf power index in the underlying coalitional game. We also show that in a certain restricted domain, where the underlying coalitional game is a weighted voting game with certain properties, it is possible to solve all of the above problems in polynomial time. We give bounds on PoM in weighted voting effort games, and provide simulation results regarding PoM in another restricted class of effort games, namely effort games played over Series‐Parallel Graphs (© 2009 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)     

On coordination of supply chain based on information asymmetry of effort level and fuzzy market environment

The agent’s private information contributes greatly to a person to make principal decision in the supply of a chain coordination. Therefore, it is a great issue for him to design an effective incentive mechanism in order to get the true information from the agent in his principle making. Assuming that the demand depend upon an agent’s effort level and the fuzzy market condition, the author in this paper researches and analyzes the principle-agent problem under fuzzy information asymmetry condition by using the theory of principal-agent as well as incentive mechanism.     

A dynamic principal-agent problem as a feedback Stackelberg differential game

We consider situations in which a principal tries to induce an agent to spend effort on accumulating a state variable that affects the well-being of both parties. The only incentive mechanism that the principal can use is a state-dependent transfer of her own utility to the agent. Formally, the model is a Stackelberg differential game in which the players use feedback strategies. Whereas in general Stackelberg differential games with feedback strategy spaces the leader’s optimization problem has non-standard features that make it extremely hard to solve, in the present case this problem can be rewritten as a standard optimal control problem. A linear-quadratic example is used to illustrate our approach.     

Normative KGP agents

We extend the logical model of agency known as the KGP model, to support agents with normative concepts, based on the roles an agent plays and the obligations and prohibitions that result from playing these roles. The proposed framework illustrates how the resulting normative concepts, including the roles, can evolve dynamically during the lifetime of the agent. Furthermore, we illustrate how these concepts can be combined with the existing capabilities of KGP agents in order to plan for their goals, react to changes in the environment, and interact with other agents. Our approach gives an executable specification of normative concepts that can be used directly for prototyping applications. Fariba Sadri is a senior lecturer at Imperial College London, from where she received her PhD. Her earlier work concentrated on integrity of deductive databases and temporal reasoning, in particular using the event calculus. In more recent years her work has been on agent technologies and multi-agent systems. She has worked on logic-based agent models, reasoning, dynamic belief revision, and inter-agent communication and negotiation for resources. She was co-awarded an EPSRC grant for research into logic-based multi-agents and was co-investigator in the EU SOCS project. Kostas Stathis is a senior lecturer at Royal Holloway, University of London and he holds a PhD from Imperial College London. His research interests are in the area of computational intelligence in general and in the intersection of computational logic and cognitive systems for social computing applications in particular. His research interests include: representation of human-computer (or computer-computer) interaction as a game; cognitive & autonomous agents; artificial agent societies; agent communication; programmable agents and agent platforms. He is a co-investigator of the EU ArguGRID project and was a co-investigator of the EU SOCS project. Francesca Toni is a senior lecturer at Imperial College London, from where she received her PhD. Her earlier work focused on abductive reasoning. In more recent years, she focused on argumentation, agent models and multi-agent systems. She has worked on computational logic-based agent models, agent reasoning, dynamic belief revision, and inter-agent communication and negotiation for resources. She has been co-ordinator of the EU SOCS project, which developed the KGP model of agency, and is coordinator of the EU ArguGRID project, on the application of argumentative agents within grid systems.     

基于模糊熵权优化的招标代理机构绩效评价研究

以《福建省工程招标代理机构信用等级评定暂行办法》、《黑龙江省工程招标代理机构信用评价暂行办法》等为依据,建立了招标代理机构绩效考核的三级评价指标体系,并运用AHP法确定绩效考核指标的主观权重值.然后,利用信息熵理论与模糊数学建立了熵权优化的绩效考核模糊综合评价模型.最后进行实例计算与分析,表明用此方法对招标代理机构进行绩效考核是科学的、合理可行的.通过将招标代理机构的收入与绩效考核结果挂钩,有利于促进其规范招标代理行为、提高服务质量.     

基于导游过度自信的激励机制设计与分析

传统的激励模型均假设委托方和代理方为完全理性的,但在旅游业中,如何对非理性(具体表现为过度自信)的导游实施有效激励是旅行社面临的更为实际的问题.利用博弈论和机制设计理论等,设计了不同信息条件下导游具有过度自信心理特征的激励机制,分析了过度自信水平对激励参数、服务努力水平、旅行社的期望效用和代理成本的影响.结果表明,与传统的激励模型相比,考虑导游过度自信的激励机制能进一步激励其提高服务努力水平,从而使旅行社的期望效用得到改善,并降低了代理成本.     

Impacts of risk attitude and outside option on compensation contracts under different information structures

We consider an agency problem where a firm (she) hires a manager (he) who has related managerial expertise to implement a new project. The manager’s managerial expertise is his private information and characterized as an uncertain variable. The revenue brought about by the project in the future is also assumed to be uncertain. In light of these challenges, this paper investigates the impacts of the manager’s risk attitude and the type-and-effort dependent outside option on the optimal compensation contracts under different information structures. Through developing the manager’s decision criterion based on his risk attitude instead of the expected-utility-maximization criterion, we find that, if the manager is conservative and the outside option’s revenue uncertainty is sufficiently high, the optimal commission rate will be distorted upwards under asymmetric managerial expertise information compared with that under symmetric managerial expertise information. Our analysis also confirms that the existence of a type-and-effort dependent outside option distorts up the compensation structure tailored at a fixed outside option. We further show that, comparing with the setting of a fixed outside option when the manager is aggressive, the presence of a type-and-effort dependent outside option results in a surprising phenomenon that the manager’s private information makes no distortion of the firm’s profit.     

Principal–agent problem for returns handling in a reverse supply chain with one manufacturer and two competing dealers

Focusing on the principal–agent problem in handling new-products returned by customers in a reverse supply chain with one manufacturer and two competing dealers, we investigate how a manufacturer motivates her dealers to exert their efforts to handle and sell the returned new-products using mathematical modelling. By taking into consideration the dealers’ individual rationalities, we design optimal incentive contracts under both symmetric and asymmetric information and obtain the following insights. In the symmetric information situation, dealers’ effort levels are identical to those maximising the expected overall profit of the supply chain. In the asymmetric information situation, however, the dealers’ effort levels are lower than the supply chain optimum. Further, in the case of intensifying competition between the dealers, their effort levels increase, while each dealer’ revenue share received from the manufacturer decreases and the risk, incentive and total agency costs of the entire supply chain tend to diminish. The revenue share is inversely correlated with return uncertainties. When we introduce another random environmental factor affecting returns into the incentive contract, this revenue share increases with a rise in dealers’ effort levels, while the above-mentioned costs of the entire system decline and this improves the supply chain system coordination. The incorporation of fairness into the principal–agent model promotes a further increase in the dealers’ effort levels, which is proved using the fixed-point theorem. Finally, we provide an example to demonstrate the main results.     

An existence result of a quasi-variational inequality associated to an equilibrium problem

In this paper we consider a Walrasian pure exchange economy with utility function which is a particular case of a general economic equilibrium problem, without production. We assume that each agent is endowed with at least of a commodity, his preferences are expressed by an utility function and it prevails a competitive behaviour: each agent regards the prices payed and received as independent of his own choices. The Walrasian equilibrium can be characterized as a solution to a quasi-variational inequality. By using this variational approach, our goal is to prove an existence result of equilibrium solutions.     

一阶条件方法的有效性及其求解分析

委托代理问题的一阶条件方法,是将代理人激励相容约束进行松弛处理,利用代理人效用函数的稳定点来代替最大化效用约束．这对于问题带来了数学处理上的方便, 但是一般情况下,这种方法是无效的．本文对于求解委托代理问题的一阶条件方法的背景,一阶条件方法的有效性,实用性进行了分析,并给出了其中一类问题的解决方法．     

Computational aspects of assigning agents to a line

We consider the problem of assigning agents to slots on a line, where only one agent can be served at a slot and each agent prefers to be served as close as possible to his target. We introduce a general approach to compute aggregate gap-minimizing assignments, as well as gap-egalitarian assignments. The approach relies on an algorithm which is shown to be faster than general purpose algorithms for the assignment problem. We also extend the approach to probabilistic assignments and explore the computational features of existing, as well as new, methods for this setting.