2022/08/04 by Tan Zhi‐Xuan, Nishad Gothoskar, Zhi-Xuan, Tan +9 · 3 citations
Computer Science · Psychology · #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Child and Animal Learning Development #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2208.02914
openalex publication_date 2022/08/04 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28
To facilitate the development of new models to bridge the gap between machine and human social intelligence, the recently proposed Baby Intuitions Benchmark (arXiv:2102.11938) provides a suite of tasks designed to evaluate commonsense reasoning about agents' goals and actions that even young infants exhibit. Here we present a principled Bayesian solution to this benchmark, based on a hierarchically Bayesian Theory of Mind (HBToM). By including hierarchical priors on agent goals and dispositions, inference over our HBToM model enables few-shot learning of the efficiency and preferences of an agent, which can then be used in commonsense plausibility judgements about subsequent agent behavior. This approach achieves near-perfect accuracy on most benchmark tasks, outperforming deep learning and imitation learning baselines while producing interpretable human-like inferences, demonstrating the advantages of structured Bayesian models of human social cognition.