Learning Multiagent Communication with Backpropagation
It addresses the challenge of multiagent collaboration in AI by automating communication learning, which is incremental as it builds on existing neural models.
The paper tackles the problem of enabling multiple agents to learn a communication protocol for cooperative tasks, resulting in improved performance over non-communicative baselines.
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.