mlsanityData to 14 Oct 2026

Learning to Ground Multi-Agent Communication with Autoencoders

arXiv 2110.15349 ↗First posted 28 Oct 2021cs.LG cs.AI cs.CLcited by 37

Not on the map. Why?

Abstract (arXiv)

Communication requires having a common language, a lingua franca, between agents. This language could emerge via a consensus process, but it may require many generations of trial and error. Alternatively, the lingua franca can be given by the environment, where agents ground their language in representations of the observed world. We demonstrate a simple way to ground language in learned representations, which facilitates decentralized multi-agent communication and coordination. We find that a standard representation learning algorithm -- autoencoding -- is sufficient for arriving at a grounded common language. When agents broadcast these representations, they learn to understand and respond to each other's utterances and achieve surprisingly strong task performance across a variety of multi-agent communication environments.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 28 of its 55 references that are in the map. First posted on arXiv 28 Oct 2021.

Builds on

28 of 55 references.

References · 28

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  7. 2016OpenAI Gymcited by 1,736
  8. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  9. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  10. 2017Counterfactual Multi-Agent Policy Gradientscited by 751
  11. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  12. 2016Learning Multiagent Communication with Backpropagationcited by 366
16 more
  1. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  2. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  3. 2020Open Problems in Cooperative AIcited by 168
  4. 2018Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Inputcited by 102
  5. 2020Learning Latent Representations to Influence Multi-Agent Interactioncited by 93
  6. 2019On the Pitfalls of Measuring Emergent Communicationcited by 71
  7. 2018Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learningcited by 68
  8. 2018Emergent Communication through Negotiationcited by 62
  9. 2019Biases for Emergent Communication in Multi-agent Reinforcement Learningcited by 48
  10. 2019Emergent Linguistic Phenomena in Multi-Agent Communication Gamescited by 36
  11. 2019A Natural Language Corpus of Common Grounding under Continuous and Partially-Observable Contextcited by 35
  12. 2018Compositional Obverter Communication Learning From Raw Visual Inputcited by 30
  13. 2021Deep Interactive Bayesian Reinforcement Learning via Meta-Learningcited by 29
  14. 2016Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networkscited by 21
  15. 2018Emergence of Communication in an Interactive World with Consistent Speakerscited by 18
  16. 2021Emergent Communication under Competitioncited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 13; 2024: 7; 2025: 3; 2026: 8.

37 papers.

Sort:

By area:

  1. 2024FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Makingcited by 113
  2. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  3. 2024Embodied LLM Agents Learn to Cooperate in Organized Teamscited by 82
  4. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  5. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communicationcited by 17
  6. 2023Semantic Channel Equalizer: Modelling Language Mismatch in Multi-User Semantic Communicationscited by 15
  7. 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
  8. 2022Towards Human-Agent Communication via the Information Bottleneck Principlecited by 8
  9. 2023Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Modelscited by 8
  10. 2022An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learningcited by 6
  11. 2025Decentralized Collective World Model for Emergent Communication and Coordinationcited by 5
  12. 2022Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learningcited by 4
25 more
  1. 2022Towards True Lossless Sparse Communication in Multi-Agent Systemscited by 4
  2. 2023Learning Multi-Object Positional Relationships via Emergent Communicationcited by 4
  3. 2023On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learningcited by 3
  4. 2023Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learningcited by 2
  5. 2023Enhancing Multi-Agent Coordination through Common Operating Picture Integrationcited by 2
  6. 2024Semantics and Spatiality of Emergent Communicationcited by 2
  7. 2025Reward-Independent Messaging for Decentralized Multi-Agent Reinforcement Learningcited by 2
  8. 2023Cooperative Multi-Agent Learning for Navigation via Structured State Abstractioncited by 1
  9. 2023DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learningcited by 1
  10. 2024ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clusteringcited by 1
  11. 2025Mixed-Initiative Dialog for Human-Robot Collaborative Manipulationcited by 1
  12. 2026SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networkingcited by 1
  13. 2022Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learningcited by 0
  14. 2023Inductive Bias for Emergent Communication in a Continuous Settingcited by 0
  15. 2023Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learningcited by 0
  16. 2023An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learningcited by 0
  17. 2023CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Makingcited by 0
  18. 2024Generalising Multi-Agent Cooperation through Task-Agnostic Communicationcited by 0
  19. 2026Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learningcited by 0
  20. 2026Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learningcited by 0
  21. 2026Generalization Bounds of Emergent Communications for Agentic AI Networkingcited by 0
  22. 2026Dreamer-CPC: Message Learning with World Models for Decentralized Multi-agent Reinforcement Learningcited by 0
  23. 2026Robust and Efficient Communication for Multi-Agent Learningcited by 0
  24. 2026Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latentscited by 0
  25. 2026Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communicationcited by 0