Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

Yat Long (Richie) Lo · Christian Schroeder de Witt · Samuel Sokota · Jakob Foerster · Shimon Whiteson

MH1-2-3-4 #115

Keywords: [ multi-agent reinforcement learning ] [ reinforcement learning ] [ Reinforcement Learning ]


Abstract:

By enabling agents to communicate, recent cooperative multi-agent reinforcement learning (MARL) methods have demonstrated better task performance and more coordinated behavior. Most existing approaches facilitate inter-agent communication by allowing agents to send messages to each other through free communication channels, i.e., \emph{cheap talk channels}. Current methods require these channels to be constantly accessible and known to the agents a priori. In this work, we lift these requirements such that the agents must discover the cheap talk channels and learn how to use them. Hence, the problem has two main parts: \emph{cheap talk discovery} (CTD) and \emph{cheap talk utilization} (CTU). We introduce a novel conceptual framework for both parts and develop a new algorithm based on mutual information maximization that outperforms existing algorithms in CTD/CTU settings. We also release a novel benchmark suite to stimulate future research in CTD/CTU.

Chat is not available.