Year: 2017
Type: conference-paper
Abstract: A number of recent works have proposed techniques for end-to-end learning of communication protocols among cooperative multi-agent populations, and have simultaneously found the emergence of grounded human-interpretable language in the protocols developed by the agents, learned without any human supervision!In this paper, using a Task & Talk reference game between two agents as a testbed, we present a sequence of 'negative' results culminating in a 'positive' one -showing that while most agent-invented languages are effective (i.e.achieve near-perfect task rewards), they are decidedly not interpretable or compositional.In essence, we find that natural language does not emerge 'naturally', despite the semblance of ease of natural-language-emergence that one may gather from recent literature.We discuss how it is possible to coax the invented languages to become more and more human-like and compositional by increasing restrictions on how two agents may communicate.
DOI: 10.18653/v1/d17-1321
Authors: Satwik Kottur, José Moura, Stefan Lee, Dhruv Batra
Language: English
Subfield: Cultural Studies
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W2730230212
