mlsanityData to 7 Oct 2026

Emergence of Grounded Compositional Language in Multi-Agent Populations

arXiv 1703.04908 ↗First posted 15 Mar 2017cs.AI cs.CLcited by 257

Not on the map. Why?

Abstract (arXiv)

By capturing statistical patterns in large corpora, machine learning has enabled significant advances in natural language processing, including in machine translation, question answering, and sentiment analysis. However, for agents to intelligently interact with humans, simply capturing the statistical patterns is insufficient. In this paper we investigate if, and how, grounded compositional language can emerge as a means to achieve goals in multi-agent populations. Towards this end, we propose a multi-agent learning environment and learning methods that bring about emergence of a basic compositional language. This language is represented as streams of abstract discrete symbols uttered by agents over time, but nonetheless has a coherent structure that possesses a defined vocabulary and syntax. We also observe emergence of non-verbal communication such as pointing and guiding when language communication is unavailable.

Key facts. Cited by 257 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 57; 2022: 43; 2023: 46; 2024: 39; 2025: 32; 2026: 39.

257 papers.

Sort:

By area:

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  2. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  3. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 281
  4. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  5. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 103
  6. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 97
  7. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  8. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  9. 2023Heterogeneous-Agent Reinforcement Learningcited by 67
  10. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  11. 2022Target-Driven Structured Transformer Planner for Vision-Language Navigationcited by 58
  12. 2021Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learningcited by 54
38 more
  1. 2021AGENT: A Benchmark for Core Psychological Reasoningcited by 42
  2. 2021Learning to Ground Multi-Agent Communication with Autoencoderscited by 37
  3. 2022Reinforced Structured State-Evolution for Vision-Language Navigationcited by 36
  4. 2021Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Taskscited by 32
  5. 2021Survey on reinforcement learning for language processingcited by 31
  6. 2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
  7. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  8. 2021On the Critical Role of Conventions in Adaptive Human-AI Collaborationcited by 26
  9. 2021Learning to Draw: Emergent Communication through Sketchingcited by 23
  10. 2022Continuously Discovering Novel Strategies via Reward-Switching Policy Optimizationcited by 23
  11. 2021Model-Based Opponent Modelingcited by 21
  12. 2021GridToPix: Training Embodied Agents with Minimal Supervisioncited by 20
  13. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  14. 2024A social path to human-like artificial intelligencecited by 20
  15. 2024TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraftcited by 20
  16. 2021Expected Value of Communication for Planning in Ad Hoc Teamworkcited by 19
  17. 2021Megaverse: Simulating Embodied Agents at One Million Experiences per Secondcited by 19
  18. 2021Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agentscited by 19
  19. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  20. 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Makingcited by 19
  21. 2021Collaborative Visual Navigationcited by 18
  22. 2021Semantic Tracklets: An Object-Centric Representation for Visual Multi-Agent Reinforcement Learningcited by 18
  23. 2021Emergent Communication under Competitioncited by 17
  24. 2021The Neural MMO Platform for Massively Multiagent Researchcited by 17
  25. 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
  26. 2021MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world modelscited by 16
  27. 2021Emergent Graphical Conventions in a Visual Communication Gamecited by 16
  28. 2022An Introduction to Multi-Agent Reinforcement Learning and Review of its Application to Autonomous Mobilitycited by 16
  29. 2022Policy Optimization for Markov Games: Unified Framework and Faster Convergencecited by 16
  30. 2024A Survey of Imitation Learning Methods, Environments and Metricscited by 16
  31. 2021HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solvingcited by 15
  32. 2024Generative Emergent Communication: Large Language Model is a Collective World Modelcited by 15
  33. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  34. 2023Games for Artificial Intelligence Research: A Review and Perspectivescited by 14
  35. 2021Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approachcited by 13
  36. 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
  37. 2021Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigationcited by 13
  38. 2022Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarizationcited by 13

50 most cited of 257 All 257 (JSON)