2022/11/04 by Boaz Carmeli, Carmeli, Boaz, Ron Meir +3
Engineering · #68T07 #Advanced Memory and Neural Computing #Artificial Intelligence (cs.AI) #Energy Harvesting in Wireless Networks #FOS: Computer and information sciences #I.2.6 #Multiagent Systems (cs.MA)
paper · pdf · doi:10.48550/arxiv.2211.02412
openalex publication_date 2022/11/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.