CLAIMay 28, 2021

Learning Approximate and Exact Numeral Systems via Reinforcement Learning

arXiv:2105.13857v29 citations
Originality Incremental advance
AI Analysis

This provides a mechanistic explanation for numeral system efficiency, potentially generalizable to other semantic domains, but is incremental as it builds on prior information-theoretic work.

The study tackled the problem of how numeral systems emerge for efficient communication by using reinforcement learning in a signaling game between two agents, resulting in numeral systems that are information-theoretically efficient and similar to human systems.

Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how efficient communication emerges via reinforcement learning. In our framework, two artificial agents play a Lewis signaling game where the goal is to convey a numeral concept. The agents gradually learn to communicate using reinforcement learning and the resulting numeral systems are shown to be efficient in the information-theoretic framework of Regier et al. (2015); Gibson et al. (2017). They are also shown to be similar to human numeral systems of same type. Our results thus provide a mechanistic explanation via reinforcement learning of the recent results in Xu et al. (2020) and can potentially be generalized to other semantic domains.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes