# Inductive Bias for Emergent Communication in a Continuous Setting

arXiv: https://arxiv.org/abs/2306.03830 · HTML: https://mlsanity.com/paper/2306.03830/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [Learning Attentional Communication for Multi-Agent Cooperation](https://mlsanity.com/paper/1805.07733/) (2018)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games](https://mlsanity.com/paper/1703.10069/) (2017)
- [On the Pitfalls of Measuring Emergent Communication](https://mlsanity.com/paper/1903.05168/) (2019)
- [Emergent Communication through Negotiation](https://mlsanity.com/paper/1804.03980/) (2018)
- [Biases for Emergent Communication in Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1912.05676/) (2019)
- [Learning to Ground Multi-Agent Communication with Autoencoders](https://mlsanity.com/paper/2110.15349/) (2021)

## Abstract (arXiv)

We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or continuous variables. We introduce an inductive bias to aid with the emergence of good communication protocols for continuous messages, and we look at the effect this type of inductive bias has for continuous and discrete messages in itself or when used in combination with reinforcement learning. We demonstrate that this type of inductive bias has a beneficial effect on the communication protocols learnt in two toy environments, Negotiation and Sequence Guess.