Emergent Quantized Communication
Keywords:MAS: Agent Communication, ML: Applications, ML: Deep Neural Architectures, ML: Representation Learning, MAS: Agent-Based Simulation and Emergent Behavior, MAS: Coordination and Collaboration, MAS: Distributed Problem Solving
AbstractThe 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 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 message. 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.
How to Cite
Carmeli, B., Meir, R., & Belinkov, Y. (2023). Emergent Quantized Communication. Proceedings of the AAAI Conference on Artificial Intelligence, 37(10), 11533-11541. https://doi.org/10.1609/aaai.v37i10.26363
AAAI Technical Track on Multiagent Systems