Algoritmo basado en Q-learning para el aprendizaje de las dificultades de los niños en las tablas de multiplicar

Jesús Pérez, Jose Aguilar, Eladio Dapena

Resumen


Para ayudar a los niños con sus dificultades con las tablas de multiplicar, este artículo presenta un sistema de aprendizaje basado en el algoritmo Q-learning, que permite a los agentes de software aprender qué tablas de multiplicar son difíciles para un niño. Los resultados indican que nuestro sistema de aprendizaje es eficaz para aprender los niveles de dificultad de los niños (bajo, medio, alto y muy alto) en las tablas de multiplicar, cuando un agente pregunta aleatoriamente todas las operaciones de las tablas de multiplicar (64 operaciones, del 2 al 9). Además, nuestro sistema de aprendizaje permite saber qué tablas de multiplicar presentan mayor dificultad con respecto a las demás, tras preguntar al menos una operación por cada tabla.

Recibido: 28 de diciembre de 2024
Aceptado: 22 de marzo de 2025


Palabras clave


Agente; robot social; Q-learning; aprendizaje por refuerzo

Texto completo:

PDF (English)

Referencias


Aguilar, J. (2014). Introducción a los Sistemas Emergentes. Talleres Gráficos, Universidad de Los Andes: Venezuela. Axelsson, A., Anderberg, E., & Haake, M. (2013). Can Preschoolers Profit from a Teachable Agent Based Play-and-Learn Game in Mathematics? In Lecture notes in computer science (pp. 289–

. https://doi.org/10.1007/978-3-642-39112-5_30

Belpaeme, T., Kennedy, J., Ramachandran, A., Scassellati, B., & Tanaka, F. (2018). Social robots for education: A review. Science Robotics, 3(21).

https://doi.org/10.1126/scirobotics.aat5954

Brown, L., & Howard, A. (2014). The positive effects of verbal encouragement in mathematics education using a social robot. In 2014 IEEE integrated STEM education conference (pp. 1-5). http://doi.org/10.1109/ISECon.2014.6891009

Castro-González, Á., Malfaz, M., & Salichs, M. A. (2011). Learning the selection of actions for an autonomous social robot by reinforcement learning based on motivations. International Journal of Social Robotics, 3(4), 427–441. https://doi.org/10.1007/s12369-011-0113-z

Jang, B., Kim, M., Harerimana, G., & Kim, J. W. (2019). Q-Learning Algorithms: A Comprehensive Classification and applications. IEEE Access, 7, 133653–133667. https://doi.org/10.1109/access.2019.2941229

Kim, Y., Thayne, J., & Wei, Q. (2016). An embodied agent helps anxious students in mathematics learning. Educational Technology Research and Development, 65(1), 219–235. https://doi.org/10.1007/s11423-016-9476-z

Liles, K. R. (2019). Ms. An (Meeting Students’ Academic Needs): Engaging Students in Math Education. Lecture Notes in Computer Science, 645–661. https://doi.org/10.1007/978-3-030-22341-0_50

Michaelis, J. & Mutlu, B. (2019). Supporting interest in science learning with a social robot. In Proceedings of the 18th ACM international

conference on interaction design and children (pp. 71-82). https://doi.org/10.1145/3311927.3323154

Mohammadhasani, N., Fardanesh, H., Hatami, J., Mozayani, N., & Fabio, R. A. (2018). The pedagogical agent enhances mathematics learning in ADHD students. Education and Information Technologies, 23(6), 2299–2308. https://doi.org/10.1007/s10639-018-9710-x

Park, H. W., Grover, I., Spaulding, S., Gomez, L., & Breazeal, C. (2019). A Model-Free affectivereinforcement learning approach to personalization of an autonomous social robot companion for early literacy education. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 687–694.

https://doi.org/10.1609/aaai.v33i01.3301687

Pareto, L. (2014). A teachable agent game engaging primary school children to learn arithmetic concepts and reasoning. International Journal of

Artificial Intelligence in Education, 24(3), 251–283. https://doi.org/10.1007/s40593-014-0018-8

Pérez, J., Aguilar, J., & Dapena, E. (2020). MIHR: a Human-Robot Interaction Model. IEEE Latin America Transactions, 18(09), 1521–1529. https://doi.org/10.1109/tla.2020.9381793

Pérez, J., Dapena, E., & Aguilar, J. (2024). Emotions as implicit feedback for adapting difficulty in tutoring systems based on reinforcement

learning. Education and Information Technologies, 29(16), 21015–21043. https://doi.org/10.1007/s10639-024-12699-8

Ramachandran, A., Huang, C. M., & Scassellati, B. (2017). Give me a break! Personalized timing strategies to promote learning in robot-child

tutoring. In Proceedings of the 2017 ACM/IEEE International Conference on Human-Robot Interaction (pp. 146-155). https://ieeexplore.ieee.org/document/8534798

Russell, S. J., & Norvig, P. (2016). Artificial Intelligence: A Modern Approach (3rd ed.).Prentice Hall Press: Upper Saddle River, USA.

Sutton, R. & Barto, A. (2018). Reinforcement Learning: An Introduction. A Bradford Book: USA.

Van Otterlo, M., & Wiering, M. (2012). Reinforcement learning and Markov decision processes. In Adaptation, learning, and optimization (pp. 3–

. https://doi.org/10.1007/978-3-642-27645-3_1

Vlachogiannis, J., & Hatziargyriou, N. (2004). Reinforcement learning for reactive power control. IEEE Transactions on Power Systems,

(3), 1317–1325. https://doi.org/10.1109/tpwrs.2004.831259

Vrochidou, E., Najoua, A., Lytridis, C., Salonidis, M., Ferelis, V., & Papakostas, G. A. (2018). Social robot NAO as a self-regulating didactic

mediator: A case study of teaching/learning numeracy. In 2018 26th international conference on software, telecommunications and computer networks (SoftCOM) (pp. 1-5). https://doi.org/10.23919/softcom.2018.8555764

Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3), 279–292. https://doi.org/10.1007/bf00992698

Zhang, D., Ding, Y., Lee, S., & Chen, J. (2016). Strategic development of multiplication problem solving: Patterns of students’ strategy

choices. The Journal of Educational Research, 110(2), 159–170. https://doi.org/10.1080/00220671.2015.1060928

Zhang, D., Xin, Y. P., Harris, K., & Ding, Y. (2013). Improving multiplication strategic development in children with math difficulties. Learning

Disability Quarterly, 37(1), 15–30. https://doi.org/10.1177/0731948713500146




Creative Commons License
Todos los documentos publicados en esta revista se distribuyen bajo una
Licencia Creative Commons Atribución -No Comercial- Compartir Igual 4.0 Internacional.
Por lo que el envío, procesamiento y publicación de artículos en la revista es totalmente gratuito.