Skip to yearly menu bar Skip to main content


Learning Multiagent Communication with Backpropagation

Sainbayar Sukhbaatar · arthur szlam · Rob Fergus

Area 5+6+7+8 #147

Keywords: [ Reinforcement Learning Algorithms ] [ Deep Learning or Neural Networks ]


Many tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. In this paper we explore a simple neural model, called CommNet, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. We apply this model to a diverse set of tasks, demonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.

Live content is unavailable. Log in and register to view live content