Ease-of-Teaching and Language Structure from Emergent Communication
Artificial Intelligence
2019-10-30 v2 Computation and Language
Machine Learning
Multiagent Systems
Abstract
Artificial agents have been shown to learn to communicate when needed to complete a cooperative task. Some level of language structure (e.g., compositionality) has been found in the learned communication protocols. This observed structure is often the result of specific environmental pressures during training. By introducing new agents periodically to replace old ones, sequentially and within a population, we explore such a new pressure -- ease of teaching -- and show its impact on the structure of the resulting language.
Cite
@article{arxiv.1906.02403,
title = {Ease-of-Teaching and Language Structure from Emergent Communication},
author = {Fushan Li and Michael Bowling},
journal= {arXiv preprint arXiv:1906.02403},
year = {2019}
}
Comments
Accepted at Neural Information Processing Systems (NeurIPS) 2019