Developmentally motivated emergence of compositional communication via template transfer

Abstract

This paper explores a novel approach to achieving emergent compositional communication in multi-agent systems. We propose a training regime implementing template transfer, the idea of carrying over learned biases across contexts. In our method, a sender-receiver pair is first trained with disentangled loss functions and then the receiver is transferred to train a new sender with a standard loss. Unlike other methods (e.g. the obverter algorithm), our approach does not require imposing inductive biases on the architecture of the agents. We experimentally show the emergence of compositional communication using topographical similarity, zero-shot generalization and context independence as evaluation metrics. The presented approach is connected to an important line of work in semiotics and developmental psycholinguistics: it supports a conjecture that compositional communication is scaffolded on simpler communication protocols.

arXiv commentAccepted for NeurIPS 2019 workshop Emergent Communication: Towards Natural Language

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Categorical Reparameterization with Gumbel-Softmax
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
• Emergence of Communication in an Interactive World with Consistent Speakers
• How agents see things: On visual representations in an emergent language game

Cited by in corpus (5)

• Towards More Human-like AI Communication: A Review of Emergent Communication Research
• Emergent Language: A Survey and Taxonomy
• Measuring non-trivial compositionality in emergent communication
• Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
• On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator