Emergent Communication through Negotiation

  title={Emergent Communication through Negotiation},
  author={Kris Cao and Angeliki Lazaridou and Marc Lanctot and Joel Z. Leibo and Karl Tuyls and Stephen Clark},
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 and is a form of cheap talk. We show that self-interested agents can use the pre-grounded… CONTINUE READING
Recent Discussions
This paper has been referenced on Twitter 47 times over the past 90 days. VIEW TWEETS

Similar Papers

Loading similar papers…