大世界中证据性合作的建模
Modeling evidential cooperation in large worlds
AI总结：
本文通过不完全信息讨价还价博弈建模大世界中的证据性合作，证明帕累托最优需最大化相同加权效用和，并论证纳什讨价还价解作为依赖均衡的合理性，同时分析信念不确定下的交易收益及联盟稳定性等开放问题。
摘要：
大世界中的证据性合作（ECL）指的是这样一种观念：人类和其他智能体可以通过在一个大宇宙中因果不相连的部分与具有不同价值观的相似智能体合作而获益。合作向智能体提供了证据，表明其他相似智能体也可能合作，从而为所有参与者带来交易收益。这对利他主义者而言可能是一个关键考量。\n我构建了一个将 ECL 刻画为不完全信息讨价还价问题的博弈论模型。该模型纳入了关于他人价值体系和经验情境的不确定性，并处理了选择折中结果的问题。利用该模型，我考察了 ECL 存在的问题，并概述了尚未解决的技术和哲学问题。\n我证明，所有合作者必须最大化相同的效用函数加权和，才能达到帕累托最优结果。然而，我反对通过归一化效用函数来隐式选择折中结果。我回顾了讨价还价理论，并论证纳什讨价还价解可能是一个相关的谢林点。我引入了依赖均衡（Spohn 2007），这是一种适用于 ECL 的均衡概念，并推广了一个民间定理，表明纳什讨价还价解是一个依赖均衡。我讨论了在关于其他智能体的信念不确定时的交易收益，并分析了在若干玩具示例中，随着对另一个智能体的信念降低，这些收益如何减少。\n最后，我讨论了我的模型中的开放问题。首先，纳什讨价还价解有时不是联盟稳定的，这意味着合作者的一个子集可以通过偏离折中结果单方面改善收益。我考察了稳定收益向量存在的条件。其次，我讨论了如何在没有 ECL 的情况下建模智能体的默认行动。
英文摘要：
Evidential cooperation in large worlds (ECL) refers to the idea that humans and other agents can benefit by cooperating with similar agents with differing values in causally disconnected parts of a large universe. Cooperating provides agents with evidence that other similar agents are likely to cooperate too, resulting in gains from trade for all. This could be a crucial consideration for altruists. I develop a game-theoretic model of ECL as an incomplete information bargaining problem. The model incorporates uncertainty about others' value systems and empirical situations, and addresses the problem of selecting a compromise outcome. Using the model, I investigate issues with ECL and outline open technical and philosophical questions. I show that all cooperators must maximize the same weighted sum of utility functions to reach a Pareto optimal outcome. However, I argue against selecting a compromise outcome implicitly by normalizing utility functions. I review bargaining theory and argue that the Nash bargaining solution could be a relevant Schelling point. I introduce dependency equilibria (Spohn 2007), an equilibrium concept suitable for ECL, and generalize a folk theorem showing that the Nash bargaining solution is a dependency equilibrium. I discuss gains from trade given uncertain beliefs about other agents and analyze how these gains decrease in several toy examples as the belief in another agent decreases. Finally, I discuss open issues in my model. First, the Nash bargaining solution is sometimes not coalitionally stable, meaning that a subset of cooperators can unilaterally improve payoffs by deviating from the compromise. I investigate conditions under which stable payoff vectors exist. Second, I discuss how to model agents' default actions without ECL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
