mlsanityData to 7 Oct 2026

Biases for Emergent Communication in Multi-agent Reinforcement Learning

arXiv 1912.05676 ↗First posted 11 Dec 2019cs.MA cs.CL cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 9; 2024: 3; 2025: 11; 2026: 3.

48 papers.

Sort:

By area:

  1. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 103
  2. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  3. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  4. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
  5. 2021Emergent Communication under Competitioncited by 17
  6. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  7. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  8. 2022Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Modelscited by 16
  9. 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 12
  10. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 11
  11. 2023Learning Multi-Agent Communication with Contrastive Learningcited by 9
  12. 2022First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximizationcited by 8
36 more
  1. 2025Echoing: Identity Failures when LLM Agents Talk to Each Othercited by 8
  2. 2022Towards Human-Agent Communication via the Information Bottleneck Principlecited by 7
  3. 2023Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translationcited by 7
  4. 2021Multi-Agent Curricula and Emergent Implicit Signalingcited by 6
  5. 2023Communication-Robust Multi-Agent Learning by Adaptable Auxiliary Multi-Agent Adversary Generationcited by 6
  6. 2021MARL with General Utilities via Decentralized Shadow Reward Actor-Criticcited by 5
  7. 2021Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-levelcited by 5
  8. 2025AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systemscited by 5
  9. 2022Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learningcited by 4
  10. 2022Over-communicate no more: Situated RL agents learn concise communication protocolscited by 4
  11. 2023Learning Multi-Object Positional Relationships via Emergent Communicationcited by 4
  12. 2021Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channelcited by 3
  13. 2022Towards True Lossless Sparse Communication in Multi-Agent Systemscited by 3
  14. 2023On the Role of Emergent Communication for Social Learning in Multi-Agent Reinforcement Learningcited by 3
  15. 2025Heterogeneous Adversarial Play in Interactive Environmentscited by 3
  16. 2022Symbol Emergence as Inter-personal Categorization with Head-to-head Latent Wordcited by 2
  17. 2022Recommendations for Systematic Research on Emergent Languagecited by 2
  18. 2022Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environmentscited by 2
  19. 2023Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learningcited by 2
  20. 2021Inference-Based Deterministic Messaging For Multi-Agent Communicationcited by 1
  21. 2021Convergence Rates of Average-Reward Multi-agent Reinforcement Learning via Randomized Linear Programmingcited by 1
  22. 2024ClusterComm: Discrete Communication in Decentralized MARL using Internal Representation Clusteringcited by 1
  23. 2024PACE: Procedural Abstractions for Communicating Efficientlycited by 1
  24. 2025GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspectivecited by 1
  25. 2025Learning what to say and how precisely: Efficient Communication via Differentiable Discrete Communication Learningcited by 1
  26. 2026DPBench: Structural Determinants of Multi-Agent LLM Coordination Under Simultaneous Resource Contentioncited by 1
  27. 2021Multi-lingual agents through multi-headed neural networkscited by 0
  28. 2023Inductive Bias for Emergent Communication in a Continuous Settingcited by 0
  29. 2023Symbol emergence as interpersonal cross-situational learning: the emergence of lexical knowledge with combinatorialitycited by 0
  30. 2025VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantizationcited by 0
  31. 2025AI-AI Esthetic Collaboration with Explicit Semiotic Awareness and Emergent Grammar Developmentcited by 0
  32. 2025AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Modelscited by 0
  33. 2025Trust-Based Social Learning for Communication (TSLEC) Protocol Evolution in Multi-Agent Reinforcement Learningcited by 0
  34. 2025Single-Agent Scaling Fails Multi-Agent Intelligence: Towards Foundation Models with Native Multi-Agent Intelligencecited by 0
  35. 2026Semantic Rate-Distortion for Bounded Multi-Agent Communication: Capacity-Derived Semantic Spaces and the Communication Cost of Alignmentcited by 0
  36. 2026Emergence, Not Bandwidth: Physical Coupling and the Limits of Learned Multi-Agent Communicationcited by 0