Source code for our paper "Learning to Communicate with Strangers via Channel Randomisation Methods"

Emergent communication in multi-agent RL

[ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer

Implementation of the Asynchronous Advantage Actor Critic with Communication in TensorFlow 2

A study of convergence of agents to a communal emergent protocol. Submitted as a part of the dissertation requirements for an MSc in Cognitive Science (2024)

Project describing how social complexity relates to communication complexity

Research project seeking to bridge the gap between representation learning and emergent communication

Emergent Communication in RLlib

Studying emergent communication among agents in cooperative and competitive environments using Reinforcement Learning, game theory and replicator dynamics

Code repository for Capacity, Bandwidth, and Compositionality in Emergent Language Learning (AAMAS 2020)

Code accompanying the blog post "Introduction to Lewis signaling games with Python"

Code for Emergent Communication under Competition (AAMAS 2021)

PyTorch implementation of "PatchGame: Learning to Signal Mid-level Patches in Referential Games" to appear in NeurIPS 2021

Code repository for On the interaction between supervision and self-play in emergent communication (ICLR 2020)

Code acompanying the paper Developmentally motivated emergence of compositional communication via template transfer

RL environment replicating the werewolf game to study emergent communication

Code accompanying the paper Measuring non-trivial compositionality in emergent communication

Emergent Communication Pretraining for Few-Shot Machine Translation

[ICLR 2022] Linking Emergent and Natural Languages via Corpus Transfer

Official PyTorch (Lightning) implementation of the NeurIPS 2020 paper "Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity".