Adapting Difficulty Levels in Personalized Robot-Child Tutoring Interactions

Social robots can be used to tutor children in one-on-one interactions. Because students have different learning needs, they consequently require complex, non-scripted teaching behaviors that adapt to the learning needs of each child. As a result of this, robot tutors are more effective given a means of adaptively customizing the pace and content of a student's curriculum. In this paper we propose a reinforcement learning-based approach that affords such capabilities to a tutoring robot, with the goals of fostering measurable learning gains and sustained engagement. We outline an architecture in which the robot uses reinforcement learning to adapt the difficulty of its exercises. Further, we describe a proposed study capable of evaluating the effectiveness of our Intelligent Tutoring System.

[1]  Joel D. Martin,et al.  Student assessment using Bayesian nets , 1995, Int. J. Hum. Comput. Stud..

[2]  Jonathan P. Rowe,et al.  When Off-Task is On-Task: The Affective Role of Off-Task Behavior in Narrative-Centered Learning Environments , 2011, AIED.

[3]  Adam Setapen,et al.  Creating robotic characters for long-term interaction , 2012 .

[4]  B. Bloom.  The 2 Sigma Problem: The Search for Methods of Group Instruction as Effective as One-to-One Tutoring , 1984 .

[5]  Lorella Giannandrea,et al.  A literature review on Intelligent Tutoring Systems and on studentprofiling , 2013 .

[6]  Kurt VanLehn,et al.  Do Micro-Level Tutorial Decisions Matter: Applying Reinforcement Learning to Induce Pedagogical Tutorial Tactics , 2010, Intelligent Tutoring Systems.

[7]  Tom Routen,et al.  Intelligent Tutoring Systems , 1996, Lecture Notes in Computer Science.

[8]  P. Winne,et al.  Handbook of educational psychology , 2015 .

[9]  J.C. Burguillo,et al.  A Qualitative Comparison of Techniques for Student Modeling in Intelligent Tutoring Systems , 2006, Proceedings. Frontiers in Education. 36th Annual Conference.

[10]  Cristina Conati,et al.  On-Line Student Modeling for Coached Problem Solving Using Bayesian Networks , 1997 .

[11]  Balaraman Ravindran,et al.  Personalized Intelligent Tutoring System Using Reinforcement Learning , 2011, FLAIRS.

[12]  John Seely Brown,et al.  Intelligent Tutoring Systems , 2016, Lecture Notes in Computer Science.

[13]  Brian Scassellati,et al.  The Physical Presence of a Robot Tutor Increases Cognitive Learning Gains , 2012, CogSci.

[14]  Joseph E. Beck,et al.  ADVISOR: A Machine Learning Architecture for Intelligent Tutor Construction , 2000, AAAI/IAAI.

[15]  Arthur C. Graesser,et al.  AutoTutor: an intelligent tutoring system with mixed-initiative dialogue , 2005, IEEE Transactions on Education.