论文标题

在没有人类数据的情况下学习强大的实时文化传播

Learning Robust Real-Time Cultural Transmission without Human Data

论文作者

Cultural General Intelligence Team, Bhoopchand, Avishkar, Brownfield, Bethanie, Collister, Adrian, Lago, Agustin Dal, Edwards, Ashley, Everett, Richard, Frechette, Alexandre, Oliveira, Yanko Gitahy, Hughes, Edward, Mathewson, Kory W., Mendolicchio, Piermaria, Pawar, Julia, Pislar, Miruna, Platonov, Alex, Senter, Evan, Singh, Sukhdeep, Zacherl, Alexander, Zhang, Lei M.

论文摘要

文化传播是领域的社会技能,它允许代理商以高保真和召回方式实时获取和使用彼此的信息。在人类中,这是遗传过程,为累积文化进化提供动力,扩大我们各代的技能,工具和知识。我们提供了一种在人工智能代理中产生零射,高回忆文化传播的方法。我们的代理商在新的环境中从人类的实时文化传播中取得了成功,而无需使用任何预先收集的人类数据。我们确定了一套令人惊讶的简单成分,足以产生文化传播,并开发一种评估方法来严格评估它。这为文化进化铺平了道路,作为发展人工智能的算法。

Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. In humans, it is the inheritance process that powers cumulative cultural evolution, expanding our skills, tools and knowledge across generations. We provide a method for generating zero-shot, high recall cultural transmission in artificially intelligent agents. Our agents succeed at real-time cultural transmission from humans in novel contexts without using any pre-collected human data. We identify a surprisingly simple set of ingredients sufficient for generating cultural transmission and develop an evaluation methodology for rigorously assessing it. This paves the way for cultural evolution as an algorithm for developing artificial general intelligence.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源