"Common Sense" and flexible learning in AI agents: Do current AI agents possess the "basic skills" necessary for them to enter the workforce?

人工智能治理的政策和制度框架依赖于有关人工智能能力的最新信息。现在，可以训练人工智能在许多单独的任务中超越人类的表现，比如对图像进行分类或分析大型数据集。然而，这些系统不能在它们接受培训的任务之外行动，而且经常在与预期投入稍有偏离的情况下发生故障(Shevlin等人，2019年)。物体持久性等基本认知技能是人类童年时期获得的灵活功能的核心，但也是人工智能面临的主要挑战(例如Voudouris等人，2022年)，它们的发展将代表着潜在应用的一步变化。然而，目前的人工智能基准既没有足够的认知定义，也没有足够的一般性来衡量这些技能的表现。这个学生将成为一个项目的一部分，该项目采用了一种新的人工智能评估方法-在概念方面(这在人工智能研究中已经很常见)和在应用全面和稳健的概念和方法框架方面都受到了认知科学的启发。由Lucy Cheke博士(认知和动机行为实验室，心理学；Leverhulme未来智能中心种类智能项目主任)和Flavia Mancini博士(计算和生物学习研究小组，工程学)联合监督，Lucy Cheke博士领导发展/比较心理学和人工智能评估研究，Flavia Mancini博士领导计算神经科学和人工智能跨学科研究小组。学生将使用深度强化和贝叶斯学习中的技术创建和训练新型人工代理，同时在动物人工智能平台(http://animalai.org))内开发一系列认知任务，以评估这些代理的能力。他们将以孩子们的表现为基准。最后，他们将与两位主管一起，学习如何使用贝叶斯和RL方法对行为数据进行计算建模，以提取不同任务中“认知指纹”的细微差别和全面理解，为使用不同架构生成的孩子和代理提供支持。

Policy and institutional frameworks for AI governance rely on up-to-date information about AI capabilities. It is now possible to train AIs to exceed human performance on numerous, individual tasks such as classifying images or analysing large datasets. However, these systems cannot act outside of the task they have been trained for and often fail under even minor deviations from their expected inputs (Shevlin et al., 2019). Basic cognitive skills such as object permanence are central to flexible function, acquired in human infanthood, but are a major challenge for AI (e.g. Voudouris et al., 2022) and their development would represent a step-change in potential applications. However, current AI benchmarks are neither sufficiently cognitively defined nor sufficiently general to measure performance in these skills.This studentship will form part of a project taking a new approach to AI evaluation - inspired by cognitive science both in terms of concepts (which is already common across AI research) and in applying a conceptual and methodological framework that is comprehensive and robust. Jointly supervised by Dr Lucy Cheke (Cognition and Motivated Behaviour Lab, Psychology; Director of the kinds of Intelligence Program, Leverhulme Centre for the Future of Intelligence), who has led research in developmental/comparative psychology and AI evaluation, and Dr Flavia Mancini (Computational and Biological Learningresearch group, Engineering), who leads an interdisciplinary research group in computational neuroscience and AI. The student will create and train novel artificial agents using techniques in Deep Reinforcement and Bayesian learning while in parallel developing a series of cognitive tasks within the Animal AI platform (http://animalai.org) to assess the capabilities of these agents. They will benchmark this performance against that of children. Finally, together with both supervisors, they will learn how to computationally model behavioral data, using both Bayesian and RL approaches, to extract a nuanced andcomprehensive understanding of the "cognitive fingerprint" across different tasks, for both children and agents generated using different architectures.