.png){kind=icon}
返回
Peano: learning formal mathematical reasoning
.png){kind=icon}
OA
AI
DOI：10.1098/rsta.2022.0044.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
General mathematical reasoning is computationally undecidable, but humans routinely solve new problems. Moreover, discoveries developed over centuries are taught to subsequent generations quickly. What structure enables this, and how might that inform automated mathematical reasoning? We posit that central to both puzzles is the structure of procedural abstractions underlying mathematics. We explore this idea in a case study on five sections of beginning algebra on the Khan Academy platform. To define a computational foundation, we introduce Peano, a theorem-proving environment where the set of valid actions at any point is finite. We use Peano to formalize introductory algebra problems and axioms, obtaining well-defined search problems. We observe existing reinforcement learning methods for symbolic reasoning to be insufficient to solve harder problems. Adding the ability to induce reusable abstractions ('tactics') from its own solutions allows an agent to make steady progress, solving all problems. Furthermore, these abstractions induce an order to the problems, seen at random during training. The recovered order has significant agreement with the expert-designed Khan Academy curriculum, and second-generation agents trained on the recovered curriculum learn significantly faster. These results illustrate the synergistic role of abstractions and curricula in the cultural transmission of mathematics.This article is part of a discussion meeting issue 'Cognitive artificial intelligence'.
Keyword:
automated theorem proving
mathematical reasoning
reinforcement learning
curriculum learning
library learning
期刊
P
IF:
3.7
论文数:
7.8K
被引数:
2.8W
机构
引用论文
.png){kind=icon}
分享收藏
Image-tube spectroscopic studies of rapid variables. III Hydrogen bombs in SS CygniS型天鹅座中快速变量的像管光谱学研究。III 氢弹OAAI
OAAI分享收藏An application of the method of least squares to the determination of the photometric elements of eclipsing binaries最小二乘法在天食双星光度元素测定中的应用
PREAI
分享收藏
查看更多内容