Social Learning through Interactions with Other Agents: A Survey

Social Learning through Interactions with Other Agents: A Survey

Dylan Hillier, Cheston Tan, Jing Jiang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Survey Track. Pages 8067-8076. https://doi.org/10.24963/ijcai.2024/892

Social learning plays an important role in the development of human intelligence. As children, we imitate our parent's 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 developmental 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 behaviour 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.
Keywords:
Machine Learning: ML: Other
Agent-based and Multi-agent Systems: MAS: Agent theories and models
Agent-based and Multi-agent Systems: MAS: Multi-agent learning
Humans and AI: HAI: Human-AI collaboration
Natural Language Processing: NLP: Dialogue and interactive systems