The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed by many to be one of the core differences between humans and neural network models. Agents can be endowed with an inductive bias towards abstraction through meta-learning, where they are trained on a distribution of tasks that share some abstract structure that can be learned and applied. However, because neural networks are hard to interpret, it can be difficult to tell whether agents have learned the underlying abstraction, or alternatively statistical patterns that are characteristic of that abstraction. In this work, we compare the performance of humans and agents in a meta-reinforcement learning paradigm in which tasks are generated from abstract rules. We define a novel methodology for building "task metamers" that closely match the statistics of the abstract tasks but use a different underlying generative process, and evaluate performance on both abstract and metamer tasks. We find that humans perform better at abstract tasks than metamer tasks whereas common neural network architectures typically perform worse on the abstract tasks than the matched metamers. This work provides a foundation for characterizing differences between humans and machine learning that can be used in future work towards developing machines with more human-like behavior.
翻译:获取抽象知识的能力是人类智力的标志,许多人认为是人类和神经网络模型之间的核心差异之一。代理商可以被赋予一种通过元学习对抽象化的感化偏向,在这种过程中,他们经过培训,可以分配一些共同抽象结构的任务,可以学习和应用。然而,由于神经网络很难解释,因此很难判断代理商是否学到了抽象的深层抽象学,或者作为这种抽象特征的统计模式。在这项工作中,我们比较了人类和代理商在从抽象规则中产生任务的元加强学习模式中的表现。我们定义了一种“task meamers”的新型方法,该方法与抽象任务的统计数据密切匹配,但使用不同的基因化过程,并评价抽象和元任务的业绩。我们发现,人类在抽象任务上的表现比元任务好,而普通的神经网络结构在抽象任务上的表现通常比相匹配的计量者要差。这项工作为区分人类和机器学习之间的差异提供了基础,这些差异可以在未来工作中用来发展机器,与更像人类的行为。</s>