This article proposes the application of the maximum-entropy principle (MEP) to agency contracting (where a principal hires an agent to make decisions on their behalf) in situations where the principal and agent only have partial knowledge on the probability distribution of the output conditioned on the agent’s actions. The paper characterizes the second-best agency contract from a maximum entropy distribution (MED) obtained from applying the MEP to the agency situation consistently with the information available. We show that, with the minimum shared information about the output distribution for the agency relationship to take place, the second-best compensation contract is (a monotone transformation of) an increasing affine function of output. With additional information on the output distribution, the second-best optimal contracts can be more complex. The second-best contracts obtained theoretically from the MEP cover many compensation schemes observed in real agency relationships.

中文翻译：

---

最大熵下的代理契约

本文提出将最大熵原则 (MEP) 应用于代理签约（委托人聘请代理人代表他们做出决策），在这种情况下委托人和代理人仅对输出的概率分布有部分了解。关于代理的行为。该论文根据最大熵分布 (MED) 描述了第二佳代理合同，该最大熵分布是将 MEP 应用于与可用信息一致的代理情况。我们表明，在关于代理关系的输出分布的最小共享信息的情况下，次优补偿合同是输出的递增仿射函数（的单调变换）。有了关于输出分布的附加信息，次优合约可能更复杂。理论上从环境保护部获得的第二好的合同涵盖了在实际代理关系中观察到的许多补偿方案。