Corpus ID: 4807923

Emergent Communication through Negotiation

  title={Emergent Communication through Negotiation},
  author={Kris Cao and A. Lazaridou and Marc Lanctot and Joel Z. Leibo and K. Tuyls and Stephen Clark},
  • Kris Cao, A. Lazaridou, +3 authors Stephen Clark
  • Published 2018
  • Computer Science
  • ArXiv
  • 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 \textit{a priori} ungrounded and is a form of cheap talk. We show that self-interested agents can use the pre… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
    • 51
    • Open Access
    Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
    • 38
    • Open Access
    Decoupling Strategy and Generation in Negotiation Dialogues
    • 30
    • Open Access
    Emergent Linguistic Phenomena in Multi-Agent Communication Games
    • 17
    • Open Access
    OpenSpiel: A Framework for Reinforcement Learning in Games
    • 21
    • Open Access
    Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
    • 61
    • Open Access
    Learning Social Conventions in Markov Games
    • 6
    Biases for Emergent Communication in Multi-agent Reinforcement Learning
    • 6
    • Open Access
    On the interaction between supervision and self-play in emergent communication
    • 10
    • Open Access


    Publications referenced by this paper.
    • 3,399
    • Open Access
    Multi-Agent Cooperation and the Emergence of (Natural) Language
    • 192
    • Open Access
    • 4,991
    • Open Access
    The Bargaining Problem
    • 6,600
    • Open Access
    Learning Multiagent Communication with Backpropagation
    • 428
    • Open Access
    Cooperative Multi-Agent Learning: The State of the Art
    • 1,096
    • Open Access
    Multi-agent Reinforcement Learning in Sequential Social Dilemmas
    • 251
    • Open Access
    Learning to Communicate with Deep Multi-Agent Reinforcement Learning
    • 521
    • Open Access
    An experimental analysis of ultimatum bargaining
    • 3,759
    • Open Access
    Multiagent reinforcement learning in the Iterated Prisoner's Dilemma.
    • 306
    • Open Access