# Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence

arXiv: https://arxiv.org/abs/1611.03218 · HTML: https://mlsanity.com/paper/1611.03218/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2016.

## Built on by (most cited first, 15 of 15)

- [Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2102.04402/) (2021)
- [Deep Multiagent Reinforcement Learning: Challenges and Directions](https://mlsanity.com/paper/2106.15691/) (2021)
- [Learning to Draw: Emergent Communication through Sketching](https://mlsanity.com/paper/2106.02067/) (2021)
- [Iterated learning for emergent systematicity in VQA](https://mlsanity.com/paper/2105.01119/) (2021)
- [Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain](https://mlsanity.com/paper/2406.17453/) (2024)
- [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)
- [MA-Dreamer: Coordination and communication through shared imagination](https://mlsanity.com/paper/2204.04687/) (2022)
- [PatchGame: Learning to Signal Mid-level Patches in Referential Games](https://mlsanity.com/paper/2111.01785/) (2021)
- [Towards Learning Abstractions via Reinforcement Learning](https://mlsanity.com/paper/2212.13980/) (2022)
- [TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2502.15425/) (2025)
- [Policy Evaluation in Decentralized POMDPs with Belief Sharing](https://mlsanity.com/paper/2302.04151/) (2023)
- [Guiding Attention in End-to-End Driving Models](https://mlsanity.com/paper/2405.00242/) (2024)
- [VQEL: Enabling Self-Play in Emergent Language Games via Agent-Internal Vector Quantization](https://mlsanity.com/paper/2503.04940/) (2025)
- [Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks](https://mlsanity.com/paper/2512.22876/) (2025)
- [Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching](https://mlsanity.com/paper/2606.10582/) (2026)

## Abstract (arXiv)

Acquiring your first language is an incredible feat and not easily duplicated. Learning to communicate using nothing but a few pictureless books, a corpus, would likely be impossible even for humans. Nevertheless, this is the dominating approach in most natural language processing today. As an alternative, we propose the use of situated interactions between agents as a driving force for communication, and the framework of Deep Recurrent Q-Networks for evolving a shared language grounded in the provided environment. We task the agents with interactive image search in the form of the game Guess Who?. The images from the game provide a non trivial environment for the agents to discuss and a natural grounding for the concepts they decide to encode in their communication. Our experiments show that the agents learn not only to encode physical concepts in their words, i.e. grounding, but also that the agents learn to hold a multi-step dialogue remembering the state of the dialogue from step to step.