mlsanityData to 7 Oct 2026

Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning

arXiv 2102.12550 ↗First posted 24 Feb 2021cs.LG cs.AI cs.MAcited by 11

Not on the map. Why?

Abstract (arXiv)

Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL). Most previous work uses continuous message communication whose high representational capacity comes at the expense of interpretability. Allowing agents to learn their own discrete message communication protocol emerged from a variety of domains can increase the interpretability for human designers and other agents.This paper proposes a method to generate discrete messages analogous to human languages, and achieve communication by a broadcast-and-listen mechanism based on self-attention. We show that discrete message communication has performance comparable to continuous message communication but with much a much smaller vocabulary size.Furthermore, we propose an approach that allows humans to interactively send discrete messages to agents.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

19 of 27 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  4. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  5. 2016Learning Multiagent Communication with Backpropagationcited by 355
  6. 2018Actor-Attention-Critic for Multi-Agent Reinforcement Learningcited by 259
  7. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 209
  8. 2018TarMAC: Targeted Multi-Agent Communicationcited by 201
  9. 2018Learning Attentional Communication for Multi-Agent Cooperationcited by 170
  10. 2016Long Short-Term Memory-Networks for Machine Readingcited by 161
  11. 2018Graph Convolutional Reinforcement Learningcited by 148
  12. 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 114
7 more
  1. 2019Deep Coordination Graphscited by 96
  2. 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 93
  3. 2019Multimodal Transformer with Multi-View Visual Representation for Image Captioningcited by 86
  4. 2019On the Pitfalls of Measuring Emergent Communicationcited by 66
  5. 2020Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learningcited by 58
  6. 2018Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Datacited by 37
  7. 2019Attentional Policies for Cross-Context Multi-Agent Reinforcement Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 8; 2024: 1.

11 papers.

  1. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  2. 2023Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translationcited by 7
  3. 2023RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learningcited by 7
  4. 2022Interpretable Learned Emergent Communication for Human-Agent Teamscited by 6
  5. 2022Towards True Lossless Sparse Communication in Multi-Agent Systemscited by 3
  6. 2023On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learningcited by 3
  7. 2023Dynamic Size Message Scheduling for Multi-Agent Communication under Limited Bandwidthcited by 1
  8. 2023Discrete Messages Improve Communication Efficiency among Isolated Intelligent Agentscited by 1
  9. 2023QMNet: Importance-Aware Message Exchange for Decentralized Multi-Agent Reinforcement Learningcited by 0
  10. 2023CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Makingcited by 0
  11. 2023Learning to Cooperate and Communicate Over Imperfect Channelscited by 0