Integrating representation learning and skill learning in a human-like intelligent agent

Abstract

Building an intelligent agent that simulates human learning of math and science could potentially benefit both cognitive science, by contributing to the understanding of human learning, and artificial intelligence, 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 research has shown that one of the key factors that differentiates 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 learning algorithms is sensitive to representation, the deep features are also important in achieving effective machine learning.In this work, we propose 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 learning agent, SimStudent, which learns procedural knowledge by observing a tutor solve sample problems, and by getting feedback while actively solving problems on its own. We show that learning representations enhances the generality of the learning agent by reducing the requirements for knowledge engineering. Moreover, we propose an approach that automatically discovers student models using the extended SimStudent. By fitting the discovered model to real student learning curve data, we show that the discovered model is better or as good as human-generated models, and demonstrate how the discovered model may be used to improve a tutoring system's instructional strategy.vi

The Application of Learning Theories into Abdullah: An Intelligent Arabic Conversational Agent Tutor

“…• A graphical user interface (GUI) that begins with an animated title screen accompanied by sound effects, to increase children's visual orientation (Marco et al, 2009). • Each lesson will start with a thoughtprovoking question or interesting fact about the selected topic to be taught, curiosity motivates students to learn .…”

Domain-General Tutor Authoring with Apprentice Learner Models

“…In the current work, we aim to evaluate the potential for apprentice learner models to support tutor authoring by assessing their applicability and efficiency across a broad range of tutors and domains. While prior work has started to quantify the efficiency gains of these models, particularly the SIMSTUDENT model (Matsuda et al 2014;Li et al 2014;Jarvis et al 2004), the past work only focuses on evaluating efficiency gains for a small subset of tutors (primarily an equation solving tutor) and domains (primarily math). Additionally, the models from these prior studies utilize domain-specific prior knowledge to support authoring in these domains, suggesting that a would-be user needs to author additional content for their domain.…”

“…Additionally, the models from these prior studies utilize domain-specific prior knowledge to support authoring in these domains, suggesting that a would-be user needs to author additional content for their domain. Li (2013) has investigated how to automatically discover domain-specific prior knowledge using unsupervised learning. However, these approaches require access to training data in one batch upfront, which may not be available for novel domains.…”

Human–machine metacommunication towards development of a human-like agent: A short review

“…However, it is still difficult to develop a completely human-like agent. Thus, researchers have developed technologies for increasing human likeness from various aspects, such as learning ability [1,2], communication and reasoning in a game [3], emotional expression in a chatbot [4], and appearance [5]. This article addresses the communication channel between a machine and a user.…”