Using Theory of Mind to Arbitrate between Social and Non-social Learning
2026-07-30 • Multiagent Systems
Multiagent Systems
AI summaryⓘ
The authors studied how people decide when to learn by watching others (social learning) versus learning by doing themselves (non-social learning). They created a model that guesses how useful it is to watch someone else based on what that person wants and what they might do next. Then, the model chooses the best option between learning socially or alone. By testing this with a game, they found their model can explain how people balance these two learning styles. This suggests that people use an understanding of others' minds to decide if social learning is worth it.
social learningnon-social learningRational Mentalizing modelTheory of Mindutility maximizationdecision makingcognitive resourcesinformativenessgame theoryhuman learning
Authors
Lance Ying, Ryan Truong, Joshua B. Tenenbaum, Samuel J. Gershman
Abstract
Social learning is a powerful mechanism through which agents learn about the world from others. However, humans sometimes choose direct experience over social learning, which can carry time and cognitive resource costs. How do people balance social and non-social learning? We propose a Rational Mentalizing model of the decision to engage in social learning. This model estimates the utility of social learning by reasoning about another agent's goal and the informativeness of their future actions. It then weighs the utility of social learning against the utility of non-social learning. Using a novel game where players choose between observing other agents or exploring the environment, we show that the Rational Mentalizing model can quantitatively capture human trade-offs between these strategies. These findings suggest that selective social learning is guided by 'Theory of Mind' in the service of utility maximization.