A Deterministic Protocol for Sequential Asymptotic Learning
A Deterministic Protocol for Sequential Asymptotic Learning
复制标题
顺序渐近学习的确定性协议
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
O. Tamuz
中科院分区：
文献类型：
--
作者：
Yu Cheng;Wade Hann;O. Tamuz
在经典的羊群行为模型中，参与者会收到关于潜在的二元自然状态的私人信号，并在观察到其前辈的行为之后按顺序采取两种可能行动中的一种。我们研究哪些类型的行为会导致渐近学习，即参与者最终将在概率上收敛到正确的行动。已知对于理性参与者和有界信号，不会出现渐近学习。如果参与者能够合作而非自私行事，会有帮助吗？如果允许参与者使用随机协议，这很容易实现。在本文中，我们提供了首个能实现渐近学习的确定性协议。此外，我们的协议具有比以往协议简单得多的优势。
In the classic herding model, agents receive private signals about an underlying binary state of nature, and act sequentially to choose one of two possible actions, after observing the actions of their predecessors. We investigate what types of behaviors lead to asymptotic learning, where agents will eventually converge to the right action in probability. It is known that for rational agents and bounded signals, there will not be asymptotic learning. Does it help if the agents can be cooperative rather than act selfishly? This is simple to achieve if the agents are allowed to use randomized protocols. In this paper, we provide the first deterministic protocol under which asymptotic learning occurs. In addition, our protocol has the advantage of being much simpler than previous protocols.