Social Learning through Interactions with Other Agents: A Survey
This is an incremental survey that synthesizes existing research on social learning in AI, highlighting gaps for researchers in embodied AI and multi-agent systems.
The paper surveys how social learning paradigms from human development are mirrored in machine learning, focusing on embodied agents and recent NLP advances, and finds that while individual techniques like imitation and feedback are successful, there is little unifying work for socially embodied agents.
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.