# Joining the Conversation: Towards Language Acquisition for Ad Hoc Team Play

arXiv: https://arxiv.org/abs/2305.12235 · HTML: https://mlsanity.com/paper/2305.12235/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 20 May 2023.

## Builds on (most cited first, 7 of 7)

- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Multi-agent Reinforcement Learning in Sequential Social Dilemmas](https://mlsanity.com/paper/1702.03037/) (2017)
- [Multi-Agent Cooperation and the Emergence of (Natural) Language](https://mlsanity.com/paper/1612.07182/) (2016)
- [Reward-rational (implicit) choice: A unifying formalism for reward learning](https://mlsanity.com/paper/2002.04833/) (2020)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Emergent Translation in Multi-Agent Communication](https://mlsanity.com/paper/1710.06922/) (2017)
- [Learning to cooperate: Emergent communication in multi-agent navigation](https://mlsanity.com/paper/2004.01097/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Review of the Applications of Deep Learning-Based Emergent Communication](https://mlsanity.com/paper/2407.03302/) (2024)
- [Decoding Communications with Partial Information](https://mlsanity.com/paper/2508.13326/) (2025)

## Abstract (arXiv)

In this paper, we propose and consider the problem of cooperative language acquisition as a particular form of the ad hoc team play problem. We then present a probabilistic model for inferring a speaker's intentions and a listener's semantics from observing communications between a team of language-users. This model builds on the assumptions that speakers are engaged in positive signalling and listeners are exhibiting positive listening, which is to say the messages convey hidden information from the listener, that then causes them to change their behaviour. Further, it accounts for potential sub-optimality in the speaker's ability to convey the right information (according to the given task). Finally, we discuss further work for testing and developing this framework.