A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning

Abstract Personalized learning is emerging in schools as an alternative to one-size-fits-all education. This study introduces and explores a weekly demand-driven flexible learning activity planning problem of own-pace own-method personalized learning. The introduced problem is a computationally intractable optimization problem involving many decision dimensions and also many soft constraints. We propose batch and decomposition methods to generate good-quality initial solutions and a dynamic Thompson sampling based hyper-heuristic framework, as a local search mechanism, which explores the large solution space of this problem in an integrative way. The characteristics of our test instances comply with average secondary schools in the Netherlands and are based on expert opinions and surveys. The experiments, which benchmark the proposed heuristics against Gurobi MIP solver on small instances, illustrate the computational challenge of this problem numerically. According to our experiments, the batch method seems quicker and also can provide better quality solutions for the instances in which resource levels are not scarce, while the decomposition method seems more suitable in resource scarcity situations. The dynamic Thompson sampling based online learning heuristic selection mechanism is shown to provide significant value to the performance of our hyper-heuristic local search. We also provide some practical insights; our experiments numerically demonstrate the alleviating effects of large school sizes on the challenge of satisfying high-spread learning demands.

[1]  Ender Özcan,et al.  Solving high school timetabling problems worldwide using selection hyper-heuristics , 2015, Expert Syst. Appl..

[2]  Graham Kendall,et al.  A Classification of Hyper-heuristic Approaches , 2010 .

[3]  Thomas R. Stidsen,et al.  Integer programming techniques for educational timetabling , 2017, Eur. J. Oper. Res..

[4]  John West-Burnham,et al.  Personalizing Learning: Transforming Education For Every Child , 2005 .

[5]  Anjuli Kannan,et al.  iSchedule to Personalize Learning , 2012, Interfaces.

[6]  Sanja Petrovic,et al.  A graph-based hyper-heuristic for educational timetabling problems , 2007, Eur. J. Oper. Res..

[7]  Vaughan Prain,et al.  Personalised learning: lessons to be learnt , 2012 .

[8]  Kees Jan Roodbergen,et al.  Design and control of warehouse order picking: A literature review , 2006, Eur. J. Oper. Res..

[9]  Grigorios N. Beligiannis,et al.  Applying evolutionary computation to the school timetabling problem: The Greek case , 2008, Comput. Oper. Res..

[10]  Michèle Sebag,et al.  Analyzing bandit-based adaptive operator selection mechanisms , 2010, Annals of Mathematics and Artificial Intelligence.

[11]  Paolo Toth,et al.  A Survey of Optimization Models for Train Routing and Scheduling , 1998, Transp. Sci..

[12]  Nelishia Pillay,et al.  A survey of school timetabling research , 2014, Ann. Oper. Res..

[13]  Ashok K. Agrawala,et al.  Thompson Sampling for Dynamic Multi-armed Bandits , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[14]  Sancho Salcedo-Sanz,et al.  A two-phase heuristic evolutionary algorithm for personalizing course timetables: a case study in a Spanish university , 2005, Comput. Oper. Res..

[15]  Barbara Bray,et al.  A Step-by-Step Guide to Personalize Learning. , 2013 .

[16]  Odd Eiken The Kunskapsskolan (“The Knowledge School”): A Personalised Approach to Education , 2011 .

[17]  Wolfgang Banzhaf,et al.  A study of heuristic combinations for hyper-heuristic systems for the uncapacitated examination timetabling problem , 2009, Eur. J. Oper. Res..

[18]  George H. G. Fonseca,et al.  Variable Neighborhood Search based algorithms for high school timetabling , 2014, Comput. Oper. Res..

[19]  Andrea Schaerf,et al.  A Survey of Automated Timetabling , 1999, Artificial Intelligence Review.

[20]  Matthias Ehrgott,et al.  Integer programming methods for large-scale practical classroom assignment problems , 2015, Comput. Oper. Res..

[21]  Michel Gendreau,et al.  A review of dynamic vehicle routing problems , 2013, Eur. J. Oper. Res..

[22]  Eddie Cheng,et al.  Flow Formulations for the Student Scheduling Problem , 2002, PATAT.

[23]  Thomas R. Stidsen,et al.  Elective course planning , 2011, Eur. J. Oper. Res..

[24]  Nelishia Pillay,et al.  A review of hyper-heuristics for educational timetabling , 2016, Ann. Oper. Res..

[25]  Michèle Sebag,et al.  Adaptive operator selection with dynamic multi-armed bandits , 2008, GECCO '08.

[26]  Luciana S. Buriol,et al.  A fix-and-optimize heuristic for the high school timetabling problem , 2014, Comput. Oper. Res..