Abstract: Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems. In this paper, we study the emergence of communication in the negotiation environment, a semi-cooperative model of agent interaction. We introduce two communication protocols - one grounded in the semantics of the game, and one which is a priori ungrounded. We show that self-interested agents can use the pre-grounded communication channel to negotiate fairly, but are unable to effectively use the ungrounded, cheap talk channel to do the same. However, prosocial agents do learn to use cheap talk to find an optimal negotiating strategy, suggesting that cooperation is necessary for language to emerge. We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation.
TL;DR: We teach agents to negotiate using only reinforcement learning; selfish agents can do so, but only using a trustworthy communication channel, and prosocial agents can negotiate using cheap talk.
Keywords: multi-agent learning, reinforcement learning, game theory, emergent communication