论文标题
紧急量化通信
Emergent Quantized Communication
论文作者
论文摘要
紧急沟通的领域旨在了解沟通的特征，因为它是从解决需要信息交换的任务的人造代理中出现的。出于科学和应用原因，与离散消息的沟通被认为是理想的特征。但是，培训具有离散通信的多代理系统并不直接，需要加强学习算法或通过连续近似（例如Gumbel-Softmax）放松离散性要求。与完全连续的交流相比，这两种解决方案都会导致性能差。在这项工作中，我们提出了一种实现离散通信的替代方法 - 通信消息的量化。使用消息量化可以使我们能够端到端训练模型，从而在多个设置中实现出色的性能。此外，量化是一个自然框架，可以从连续到离散的通信中运行范围。因此，它为深度学习时代的多机构沟通的更广泛的看法树立了基础。
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.
