Corpus ID: 56895453

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

@article{Singh2019LearningWT,
  title={Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks},
  author={Amanpreet Singh and Tushar Jain and Sainbayar Sukhbaatar},
  journal={ArXiv},
  year={2019},
  volume={abs/1812.09755}
}
  • Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but have been restricted to fully-cooperative tasks. In this paper, we present Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive… CONTINUE READING
    TarMAC: Targeted Multi-Agent Communication
    46
    Learning Structured Communication for Multi-agent Reinforcement Learning
    Learning Multi-Agent Coordination through Graph-driven Communication.
    MEMORY-DRIVEN COMMUNICATION
    R-MADDPG for Partially Observable Environments and Limited Communication
    5
    When2com: Multi-Agent Perception via Communication Graph Grouping
    1
    Learning Nearly Decomposable Value Functions Via Communication Minimization
    10

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 37 REFERENCES
    Learning to Communicate with Deep Multi-Agent Reinforcement Learning
    501
    Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games
    125
    Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
    694
    Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability
    170
    Multi-Agent Reinforcement Learning: Independent versus Cooperative Agents
    418
    Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
    107
    Cooperative Multi-Agent Learning: The State of the Art
    1086
    Cooperative Multi-agent Control Using Deep Reinforcement Learning
    212