Social Learning through Interactions with Other Agents: A Survey

TL;DR

This survey explores how social learning principles from human development are being integrated into machine learning, highlighting recent advances and the need for unified approaches in embodied social agents.

Contribution

It provides a comprehensive overview of social learning techniques in machine learning and identifies the gap in unifying these methods into embodied social agents.

Findings

Social learning techniques are successfully applied individually.

Recent NLP advances enable new social learning forms.

Lack of unified frameworks for embodied social agents.

Abstract

Social learning plays an important role in the development of human intelligence. As children, we imitate our parents' speech patterns until we are able to produce sounds; we learn from them praising us and scolding us; and as adults, we learn by working with others. In this work, we survey the degree to which this paradigm -- social learning -- has been mirrored in machine learning. In particular, since learning socially requires interacting with others, we are interested in how embodied agents can and have utilised these techniques. This is especially in light of the degree to which recent advances in natural language processing (NLP) enable us to perform new forms of social learning. We look at how behavioural cloning and next-token prediction mirror human imitation, how learning from human feedback mirrors human education, and how we can go further to enable fully communicative agents that learn from each other. We find that while individual social learning techniques have been used successfully, there has been little unifying work showing how to bring them together into socially embodied agents.