K.R.: Integrating representation learning and skill learning in a human-like intelligent agent

Building an intelligent agent that simulates human learning of math and science could potentially benefit both education, by contributing to the understanding of human learning, and artificial intel-ligence, by advancing the goal of creating human-level intelligence. However, constructing such a learning agent currently requires manual encoding of prior domain knowledge; in addition to being a poor model of human acquisition of prior knowledge, manual knowledge-encoding is both time-consuming and error-prone. Previous work showed that one of the key factors that differen-tiates experts and novices is their different representations of knowledge. Experts view the world in terms of deep functional features, while novices view it in terms of shallow perceptual features. Moreover, since the performance of many existing learning algorithms is sensitive to representa-tion, the deep features are also important in achieving effective learning. In this paper, we present an efficient algorithm that acquires representation knowledge in the form of “deep features ” for specific domains, and demonstrate its effectiveness in the domain of algebra as well as synthetic domains. We integrate this algorithm into a machine-learning agent, SimStudent, which learns procedural knowledge by observing a tutor solve sample problems, and by getting feedback whil