Software 1.0 Strengths for Interpretability and Data Efficiency

Maral Jabbarishiviari, Arshia Soltani Moakhar

Keywords: ReInforcement Learning, programming language design

TL;DR: We suggest Learnable if statements as a RL interface in software programming, letting programmers use RL, producing interpretable intelligence systems.

Abstract: Machine learning has demonstrated remarkable capabilities across various tasks, yet it confronts significant challenges such as limited interpretability, reliance on extensive data, and difficulties in incorporating human intuition. In contrast, traditional software development avoids these pitfalls, offering full interpretability, less data dependency, and easy integration of intuitive decision-making. To have the strengths of both approaches, we introduce the BasedOn library. This tool focuses on code written by programmers while providing very simple interfaces to let programmers use machine learning. The BasedOn library, leveraging policy gradient methods, offers "learnable" if statements.

Submission Number: 246