Model analysis for pedagogical decision-making in an environment focused on learning algorithms

• Djefferson S. S. Maranhão UFMA
• Antonio Carlos Raposo UFMA
• Carlos de Salles Soares Neto Universidade Federal do Maranhão

DOI: https://doi.org/10.5753/cbie.sbie.2020.1223

Abstract

This paper analyzes qualitatively the use of POMDP as a model for making pedagogical decisions in an environment focused on learning algorithms. The issue to be faced is the sequencing of computational problems in intelligent tutoring environments, since it is common practice to propose computational problems in introductory algorithm courses. The sequencing of activities was seen as a sequential decision process under uncertainty, since thetutor does not know exactly what knowledge state the student is currently in.The main contribution of this work was to show that the model can be applied satisfactorily to the intelligent tutoring process, considering that students wereguided by the paths that offered the greatest gains in knowledge.

Keywords: Pedagogical Decisions, Algorithms Learning, POMDP

References

Bez, J. L., Tonin, N. A., and Rodegheri, P. R. (2014). Uri online judge academic: A tool for algorithms and programming classes. In 2014 9th International Conference on Computer Science Education, pages 149–152.


Kolobov, A. (2013).Scalable methods and expressive models for planning under uncer-tainty. PhD thesis.


Lister, R., Adams, E. S., Fitzgerald, S., Fone, W., Hamer, J., Lindholm, M., McCartney, R., Mostr ̈om, J. E., Sanders, K., Sepp ̈al ̈a, O., et al. (2004). A multi-national study of reading and tracing skills in novice programmers.ACM SIGCSE Bulletin, 36(4):119–150.


McCracken, M., Almstrum, V., Diaz, D., Guzdial, M., Hagan, D., Kolikant, Y. B.-D.,Laxer, C., Thomas, L., Utting, I., and Wilusz, T. (2001). A multi-national, multi-institutional study of assessment of programming skills of first-year cs students. In Working group reports from ITiCSE on Innovation and technology in computer science education, pages 125–180.


Pineau, J., Gordon, G., Thrun, S., et al. (2003). Point-based value iteration: An anytime algorithm for pomdps. In IJCAI, volume 3, pages 1025–1032.


Rafferty, A. N., Brunskill, E., Griffiths, T. L., and Shafto, P. (2011). Faster teaching by pomdp planning. InInternational Conference on Artificial Intelligence in Education, pages 280–287. Springer.


Revilla, M. A., Manzoor, S., and Liu, R. (2008). Competitive learning in informatics:The uva online judge experience. Olympiads in Informatics, 2(10):131–148.


Smallwood, R. D. and Sondik, E. J. (1973). The optimal control of partially observable markov processes over a finite horizon. Operations research, 21(5):1071–1088.


Somani, A., Ye, N., Hsu, D., and Lee, W. S. (2013). Despot: Online pomdp planning with regularization. In Advances in neural information processing systems, pages 1772–1780.


Ten Pas, A. (2012). Simulation based planning for partially observable markov decision processes with continuous observation spaces. Master’s thesis, Faculty of Humanities and Sciences, Maastricht University.


Theocharous, G., Beckwith, R., Butko, N., and Philipose, M. (2009). Tractable pomdp planning algorithms for optimal teaching in “spais”. In IJCAI PAIR Workshop.


Van Otterlo, M. and Wiering, M. (2012). Reinforcement learning and markov decision processes. In Reinforcement Learning, pages 3–42. Springer.


Wang, F. (2018). Reinforcement learning in a pomdp based intelligent tutoring system for optimizing teaching strategies. International Journal of Information and Education Technology, 8(8).


Woolf, B. P. (2010).Building intelligent interactive tutors: Student-centered strategies for revolutionizing e-learning. Morgan Kaufmann.


Zhang, P. (2013).Using POMDP-based reinforcement learning for online optimization of teaching strategies in an intelligent tutoring system. PhD thesis.