arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.02308cs.AI
收藏

无模型、基于模型和通用智能

Model-free, Model-based, and General Intelligence

Universitat Pompeu Fabra(庞培法布拉大学);ICREA(加泰罗尼亚研究与高级研究理事会(ICREA))

Hector Geffner

摘要:

在60年代和70年代,人工智能研究人员通过编写显示智能行为的程序来探索关于智能的直觉。许多好的想法都是从这项工作中产生的,但是手工编写的程序并不健壮或通用。80年代后,研究越来越多地转向开发能够从经验和数据推断行为和功能的学习者,以及能够处理定义良好但难以处理的模型(如SAT,经典规划,贝叶斯网络和POMDPs)的求解器。学习方法取得了相当大的成功,但结果是黑盒,不具有灵活性,透明度和基于模型的同行的一般性。另一方面,基于模型的方法需要模型和可扩展的算法。无模型学习器和基于模型的求解器与当前人类思维理论中的系统1和系统2有着密切的相似之处:第一,快速、不透明和不灵活的直觉思维;第二,缓慢、透明和灵活的分析思维。在本文中,我回顾了人工智能的发展,并利用这些理论来讨论无模型学习器和基于模型的求解器之间的差距,为了拥有强大且通用的智能系统,需要弥合这一差距。

英文摘要:

During the 60s and 70s, AI researchers explored intuitions about intelligence by writing programs that displayed intelligent behavior. Many good ideas came out from this work but programs written by hand were not robust or general. After the 80s, research increasingly shifted to the development of learners capable of inferring behavior and functions from experience and data, and solvers capable of tackling well-defined but intractable models like SAT, classical planning, Bayesian networks, and POMDPs. The learning approach has achieved considerable success but results in black boxes that do not have the flexibility, transparency, and generality of their model-based counterparts. Model-based approaches, on the other hand, require models and scalable algorithms. Model-free learners and model-based solvers have close parallels with Systems 1 and 2 in current theories of the human mind: the first, a fast, opaque, and inflexible intuitive mind; the second, a slow, transparent, and flexible analytical mind. In this paper, I review developments in AI and draw on these theories to discuss the gap between model-free learners and model-based solvers, a gap that needs to be bridged in order to have intelligent systems that are robust and general.

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。

↑