Multi-lingual agents through multi-headed neural networks
arXiv:2111.11129
Abstract
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.
arXiv commentCooperative AI workshop NeurIPS 2021
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning to Communicate with Deep Multi-Agent Reinforcement Learning
- Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
- "Other-Play" for Zero-Shot Coordination
- Biases for Emergent Communication in Multi-agent Reinforcement Learning
- Quasi-Equivalence Discovery for Zero-Shot Emergent Communication