Emergent Quantized Communication
This work addresses a bottleneck in emergent communication for AI researchers, offering a more effective approach to discrete messaging in multi-agent tasks.
The paper tackles the challenge of achieving discrete communication in multi-agent systems, which typically suffer from poor performance compared to continuous communication, by proposing message quantization as an end-to-end training method that achieves superior performance in multiple setups.
The field of emergent communication aims to understand the characteristics of communication as it emerges from artificial agents solving tasks that require information exchange. Communication with discrete messages is considered a desired characteristic, for both scientific and applied reasons. However, training a multi-agent system with discrete communication is not straightforward, requiring either reinforcement learning algorithms or relaxing the discreteness requirement via a continuous approximation such as the Gumbel-softmax. Both these solutions result in poor performance compared to fully continuous communication. In this work, we propose an alternative approach to achieve discrete communication -- quantization of communicated messages. Using message quantization allows us to train the model end-to-end, achieving superior performance in multiple setups. Moreover, quantization is a natural framework that runs the gamut from continuous to discrete communication. Thus, it sets the ground for a broader view of multi-agent communication in the deep learning era.