论文标题
用层次的贝叶斯思想解决婴儿直觉基准
Solving the Baby Intuitions Benchmark with a Hierarchically Bayesian Theory of Mind
论文作者
论文摘要
为了促进开发新模型以弥合机器与人类社会情报之间的差距，最近提出的婴儿直觉基准（Arxiv：2102.11938）提供了一系列任务，旨在评估有关代理商的目标和行动，甚至是年轻的婴儿都展现的。在这里，我们根据层次的贝叶斯心理理论（HBTOM）提出了该基准的原则性贝叶斯解决方案。通过在代理目标和处置上包括层次的先验，对我们的HBTOM模型的推断几乎可以学习代理的效率和偏好，然后可以将其用于常识性的合理性判断，以判断有关后续代理行为。这种方法在大多数基准任务上实现了几乎完美的准确性，在产生可解释的人类的推论的同时，超过了深度学习和模仿学习基准，证明了结构化贝叶斯人类社会认知模型的优势。
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.
