偏离路径一步的理性学习
Rational Learning One Step Off the Path
浏览论文内容
中文总结 AI 辅助
该研究在Fudenberg和Levine的世代交叠学习模型中，证明当智能体寿命足够长且足够耐心时，偏离主流行为的单次行为可修正错误信念，极限博弈结果与子博弈确认均衡路径等价，确立了其2006年结论的逆命题。
中文摘要 AI 辅助
哪些社会规范在理性学习下是自我修正的？我们证明，若偏离主流行为的单次行为能产生反对错误信念的证据，那么由错误信念维持的行为就无法持续。我们研究Fudenberg和Levine（1993）的世代交叠学习模型，其中有限寿命的贝叶斯智能体被反复随机匹配其他角色的智能体，仅观察自身匹配情况并从经验中学习。在具有节点wise独立非退化先验的简单扩展式博弈中，当智能体寿命足够长且足够耐心时，每个极限博弈结果都与子博弈确认均衡路径等价，这确立了Fudenberg和Levine（2006）的逆命题。其机制是内生实验：对潜在盈利偏离后果的不确定性，给予耐心智能体测试该偏离的动机，产生的观测结果可修正信念并约束后续博弈。
英文摘要
Which social norms are self-correcting under rational learning? We show that conduct sustained by false beliefs cannot persist if a single departure from prevailing behavior generates evidence against those beliefs. We study the overlapping-generations learning model of Fudenberg and Levine (1993), in which finitely lived Bayesian agents are repeatedly and randomly matched with agents in other player roles, observe only their own matches, and learn from experience. In simple extensive-form games with nodewise-independent, nondegenerate priors, as agents live increasingly long lives and become sufficiently patient, every limiting game outcome is path-equivalent to a subgame-confirmed equilibrium. This establishes the converse of Fudenberg and Levine (2006). The mechanism is endogenous experimentation: uncertainty about the consequences of a potentially profitable departure gives patient agents an incentive to test it, generating the observations that correct beliefs and discipline continuation play.
