# Multi-lingual agents through multi-headed neural networks

arXiv: https://arxiv.org/abs/2111.11129 · HTML: https://mlsanity.com/paper/2111.11129/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- ["Other-Play" for Zero-Shot Coordination](https://mlsanity.com/paper/2003.02979/) (2020)
- [Graph Convolutional Reinforcement Learning](https://mlsanity.com/paper/1810.09202/) (2018)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Biases for Emergent Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1912.05676/) (2019)
- [A New Formalism, Method and Open Issues for Zero-Shot Coordination](https://mlsanity.com/paper/2106.06613/) (2021)
- [Quasi-Equivalence Discovery for Zero-Shot Emergent Communication](https://mlsanity.com/paper/2103.08067/) (2021)

## Abstract (arXiv)

This paper considers cooperative Multi-Agent Reinforcement Learning, focusing on emergent communication in settings where multiple pairs of independent learners interact at varying frequencies. In this context, multiple distinct and incompatible languages can emerge. When an agent encounters a speaker of an alternative language, there is a requirement for a period of adaptation before they can efficiently converse. This adaptation results in the emergence of a new language and the forgetting of the previous language. In principle, this is an example of the Catastrophic Forgetting problem which can be mitigated by enabling the agents to learn and maintain multiple languages. We take inspiration from the Continual Learning literature and equip our agents with multi-headed neural networks which enable our agents to be multi-lingual. Our method is empirically validated within a referential MNIST based communication game and is shown to be able to maintain multiple languages where existing approaches cannot.