# Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game

arXiv: https://arxiv.org/abs/1911.01892 · HTML: https://mlsanity.com/paper/1911.01892/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Nov 2019.

## Built on by (most cited first, 7 of 7)

- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off](https://mlsanity.com/paper/2301.13083/) (2023)
- [The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs](https://mlsanity.com/paper/2602.11583/) (2026)
- [Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks](https://mlsanity.com/paper/2201.05489/) (2022)
- [ELCC: the Emergent Language Corpus Collection](https://mlsanity.com/paper/2407.04158/) (2024)
- [Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations](https://mlsanity.com/paper/2609.06025/) (2026)

## Abstract (arXiv)

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.