mlsanityData to 7 Oct 2026

Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition

arXiv 2402.16247 ↗First posted 26 Feb 2024cs.LG cs.CL cs.MAcited by 1

Not on the map. Why?

Abstract (arXiv)

In Emergent Communication (EC) agents learn to communicate with one another, but the protocols that they develop are specialised to their training community. This observation led to research into Zero-Shot Coordination (ZSC) for learning communication strategies that are robust to agents not encountered during training. However, ZSC typically assumes that no prior data is available about the agents that will be encountered in the zero-shot setting. In many cases, this presents an unnecessarily hard problem and rules out communication via preestablished conventions. We propose a novel AI challenge called a Cooperative Language Acquisition Problem (CLAP) in which the ZSC assumptions are relaxed by allowing a 'joiner' agent to learn from a dataset of interactions between agents in a target community. We propose and compare two methods for solving CLAPs: Imitation Learning (IL), and Emergent Communication pretraining and Translation Learning (ECTL), in which an agent is trained in self-play with EC and then learns from the data to translate between the emergent protocol and the target community's protocol.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 36 references that are in the map. First posted on arXiv 26 Feb 2024.

Builds on

14 of 36 references.

References · 14

  1. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  2. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  3. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  4. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  5. 2016Learning Multiagent Communication with Backpropagationcited by 355
  6. 2020"Other-Play" for Zero-Shot Coordinationcited by 194
  7. 2020Emergent Multi-Agent Communication in the Deep Learning Eracited by 168
  8. 2020Toward the Fundamental Limits of Imitation Learningcited by 96
  9. 2021Off-Belief Learningcited by 72
  10. 2019On the Pitfalls of Measuring Emergent Communicationcited by 66
  11. 2023Cooperative Open-ended Learning Framework for Zero-shot Coordinationcited by 30
  12. 2021Quasi-Equivalence Discovery for Zero-Shot Emergent Communicationcited by 19
2 more
  1. 2020Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populationscited by 18
  2. 2021Learning to Communicate with Strangers via Channel Randomisation Methodscited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Decoding Communications with Partial Informationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025In-Context Reinforcement Learning via Communicative World Models
  2. 2019Learning to Request Guidance in Emergent Communication
  3. 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
  4. 2025Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
  5. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  6. 2023Progressively Efficient Learning
  7. 2023ProAgent: Building Proactive Cooperative Agents with Large Language Models
  8. 2024Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control