AIRCC's International Journal of Computer Science and Information Technology

Open Access Open Access  Restricted Access Subscription Access

Reinforcement Learning in Education 4.0: Open Applications and Deployment Challenges


Affiliations
1 Department of ICT Education, University of Education, Winneba, Ghana
 

Education 4.0 involves adopting technology in teaching and learning to drive innovation and growth across academic institutions. Artificial Intelligence and Machine Learning are frontrunners in Education 4.0, having already impacted diverse sectors globally. Since the COVID-19 pandemic, the conventional method of teaching and learning has become unpopular among institutions and is currently being replaced with intelligent educational data pattern identification and online learning. The teacher-centred pedagogical paradigm has significantly shifted to a learner-centred pedagogy with the emergence of Education 4.0. Reinforcement Learning has been deployed successfully in diverse sectors, and the educational domain should not be an exemption. This survey discusses Reinforcement Learning, a feedback-based machine learning technique, with application modules in the academic field. Each module is analysed for the state-action-reward implementation policies with relevant features that define individual use cases. The survey primarily examined the classroom, admission, e-learning, library and game development modules. In addition, the survey heightened the foreseeable challenges in the real-world deployment of Reinforcement Learning in educational institutions.

Keywords

Education 4.0, Reinforcement Learning, Smart Campus, Intelligent Objects, Artificial Intelligence, Machine Learning.
User
Notifications
Font Size

  • L. M. Castro Benavides, J. A. Tamayo Arias, M. D. Arango Serna, J. W. Branch Bedoya, and D. Burgos, “Digital Transformation in Higher Education Institutions: A Systematic Literature Review,” Sensors (Basel)., vol. 20, no. 11, pp. 1–22, 2020, doi: 10.3390/s20113291.

  • N. Bremner, “ResearchSPAce,” pp. 53–64, 2019.

  • A. Mikroyannidis, J. Domingue, M. Bachler, and K. Quick, “A Learner-Centred Approach for Lifelong Learning Powered by the Blockchain,” EdMedia + Innov. Learn. 2018, pp. 1388–1393, 2018, [Online]. Available: http://uk.businessinsider.com/santander-has-20-25-use-cases-for-bitcoins-blockchain-technology-everyday-banking-2015-6%0Ahttps://www.semanticscholar.org/paper/A-Learner-Centred-Approach-for-Lifelong-Learningby-Domingue-Bachler/ce096256873ab23915eb39312de.

  • D. Majumdar, P. K. Banerji, and S. Chakrabarti, “Disruptive technology and disruptive innovation: ignore at your peril!,” Technol. Anal. Strateg. Manag., vol. 30, no. 11, pp. 1247–1255, 2018, doi: 10.1080/09537325.2018.1523384.

  • H. Akoto-Baako, P. J. Heeralal, and B. Kissi-Abrokwah, “Concept of Increase Enrolment: Its effect on teachers in Ghana,” Mediterr. J. Soc. Sci., vol. 12, no. 6, p. 167, 2021, doi: 10.36941/mjss-2021-0066.

  • A. Serrano Mamolar, P. Salvá-García, E. Chirivella-Perez, Z. Pervez, J. M. Alcaraz Calero, and Q. Wang, “Autonomic protection of multi-tenant 5G mobile networks against UDP flooding DDoS attacks,” J. Netw. Comput. Appl., vol. 145, no. November 2018, p. 102416, 2019, doi: 10.1016/j.jnca.2019.102416.

  • A. Mirahmadizadeh et al., “Evaluation of students’ attitude and emotions towards the sudden closure of schools during the COVID-19 pandemic: a cross-sectional study,” BMC Psychol., vol. 8, no. 1, pp. 1–7, 2020, doi: 10.1186/s40359-020-00500-7.

  • A. M. Müller, C. Goh, L. Z. Lim, and X. Gao, “Covid-19 emergency elearning and beyond: Experiences and perspectives of university educators,” Educ. Sci., vol. 11, no. 1, pp. 1–15, 2021, doi: 10.3390/educsci11010019.

  • M. O. Riedl, “Human-centered artificial intelligence and machine learning,” Hum. Behav. Emerg. Technol., vol. 1, no. 1, pp. 33–36, 2019, doi: 10.1002/hbe2.117.

  • V. Kuleto et al., “Exploring opportunities and challenges of artificial intelligence and machine learning in higher education institutions,” Sustain., vol. 13, no. 18, pp. 1–16, 2021, doi: 10.3390/su131810424.

  • M. van der Schaar et al., “How artificial intelligence and machine learning can help healthcare systems respond to COVID-19,” Mach. Learn., vol. 110, no. 1, pp. 1–14, 2021, doi: 10.1007/s10994-020-05928-x.

  • M. Ghobakhloo, “Industry 4.0, digitization, and opportunities for sustainability,” J. Clean. Prod., vol. 252, p. 119869, 2020, doi: 10.1016/j.jclepro.2019.119869.

  • C. Bai, P. Dallasega, G. Orzes, and J. Sarkis, “Industry 4.0 technologies assessment: A sustainability perspective,” Int. J. Prod. Econ., vol. 229, p. 107776, 2020, doi: 10.1016/j.ijpe.2020.107776.

  • A. H. Anaelka, “Education 4.0 Made Simple: Ideas For Teaching,” Int. J. Educ. Lit. Stud., vol. 6, no. 3, p. 92, 2018, [Online]. Available: https://journals.aiac.org.au/index.php/IJELS/article/view/4616.

  • R. Kasih, N. Hanafi, and M. Amin, “Education 4.0 and the 21st Century Skills: A Case Study of Smartphone Use in English Classes,” vol. 465, no. Access 2019, pp. 48–51, 2020, doi: 10.2991/assehr.k.200827.013.

  • M. Batta, “Machine Learning Algorithms - A Review ,” Int. J. Sci. Res. (IJ, vol. 9, no. 1, pp. 381-undefined, 2020, doi: 10.21275/ART20203995.

  • R. Saravanan and P. Sujatha, “Algorithms : A Perspective of Supervised Learning Approaches in Data Classification,” 2018 Second Int. Conf. Intell. Comput. Control Syst., no. Iciccs, pp. 945–949, 2018, [Online]. Available: https://ieeexplore.ieee.org/abstract/document/8663155.

  • D. K. Dake, J. D. Gadze, G. S. Klogo, and H. Nunoo-mensah, “Multi-Agent Reinforcement Learning Framework in SDN-IoT for Transient Load Detection and Prevention,” 2021.

  • M. A. Yasin, W. A. M. Al-Ashwal, A. M. Shire, S. A. Hamzah, and K. N. Ramli, “Tri-band planar inverted F-antenna (PIFA) for GSM bands and bluetooth applications,” ARPN J. Eng. Appl. Sci., vol. 10, no. 19, pp. 8740–8744, 2015.

  • E. Asiain, J. B. Clempner, and A. S. Poznyak, “Controller exploitation-exploration reinforcement learning architecture for computing near-optimal policies,” Soft Comput., vol. 23, no. 11, pp. 3591–3604, 2019, doi: 10.1007/s00500-018-3225-7.

  • M. Van Otterlo and M. Wiering, “Reinforcement learning and markov decision processes,” Adapt. Learn. Optim., vol. 12, pp. 3–42, 2012, doi: 10.1007/978-3-642-27645-3_1.

  • D. K. Dake, G. S. Klogo, J. D. Gadze, and H. Nunoo-Mensah, “Traffic Engineering in Software-defined Networks using Reinforcement Learning: A Review,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 5, pp. 330–345, 2021, doi: 10.14569/IJACSA.2021.0120541.

  • L. Canese et al., “Multi-agent reinforcement learning: A review of challenges and applications,” Appl. Sci., vol. 11, no. 11, 2021, doi: 10.3390/app11114948.

  • A. S. Polydoros and L. Nalpantidis, “Survey of Model-Based Reinforcement Learning: Applications on Robotics,” J. Intell. Robot. Syst. Theory Appl., vol. 86, no. 2, pp. 153–173, 2017, doi: 10.1007/s10846-017-0468-y.

  • T. Degris, P. M. Pilarski, and R. S. Sutton, “Model-Free reinforcement learning with continuous action in practice,” Proc. Am. Control Conf., pp. 2177–2182, 2012, doi: 10.1109/acc.2012.6315022.

  • M. Hausknecht, P. Stone, and O. Mc, “On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning,” Ijcai, 2016.

  • S. Fujimoto, H. Van Hoof, and D. Meger, “Addressing Function Approximation Error in Actor-Critic Methods,” 35th Int. Conf. Mach. Learn. ICML 2018, vol. 4, pp. 2587–2601, 2018.

  • H. Qie, D. Shi, T. Shen, X. Xu, Y. Li, and L. Wang, “Joint Optimization of Multi-UAV Target Assignment and Path Planning Based on Multi-Agent Reinforcement Learning,” IEEE Access, vol. 7, pp. 146264–146272, 2019, doi: 10.1109/ACCESS.2019.2943253.

  • H. U. Sheikh and L. Boloni, “Multi-Agent Reinforcement Learning for Problems with Combined Individual and Team Reward,” Proc. Int. Jt. Conf. Neural Networks, 2020, doi: 10.1109/IJCNN48605.2020.9206879.

  • A. Hassan, N. Z. Abiddin, and S. K. Yew, “The Philosophy of Learning and Listening in Traditional Classroom and Online Learning Approaches,” High. Educ. Stud., vol. 4, no. 2, pp. 19–28, 2014, doi: 10.5539/hes.v4n2p19.

  • S. Hartikainen, H. Rintala, L. Pylväs, and P. Nokelainen, “The concept of active learning and the measurement of learning outcomes: A review of research in engineering higher education,” Educ. Sci., vol. 9, no. 4, pp. 9–12, 2019, doi: 10.3390/educsci9040276.

  • A. G. Barto, P. S. Thomas, and R. S. Sutton, “Some recent applications of reinforcement learning,” Work. Adapt. Learn. Syst., p. 6, 2017, [Online]. Available: http://psthomas.com/papers/Barto2017.pdf.

  • E. Gyimah, D. K. Dake, and M. Agbeko, “The Role of Computer Games in the Learning of Programming among Tertiary Students in Ghana,” African J. Appl. Res., vol. 4, no. 2, pp. 242–252, 2018.

  • E. Sudarmilah, U. Fadlilah, H. Supriyono, F. Y. Al Irsyadi, Y. S. Nugroho, and A. Fatmawati, “A review: Is there any benefit in serious games?,” AIP Conf. Proc., vol. 1977, no. June 2018, 2018, doi: 10.1063/1.5042915.

  • A. Dobrovsky, C. W. Wilczak, P. Hahn, M. Hofmann, and U. M. Borghoff, “Deep Reinforcement Learning in Serious Games: Analysis and Design of Deep Neural Network Architectures,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 10672 LNCS, pp. 314–321, 2018, doi: 10.1007/978-3-319-74727-9_37.

  • I. Szita, “Reinforcement learning in games,” Adapt. Learn. Optim., vol. 12, pp. 539–577, 2012, doi: 10.1007/978-3-642-27645-3_17.

  • A. Dobrovsky, U. M. Borghoff, and M. Hofmann, “Applying and augmenting deep reinforcement learning in serious games through interaction,” Period. Polytech. Electr. Eng. Comput. Sci., vol. 61, no. 2, pp. 198–208, 2017, doi: 10.3311/PPee.10313.

  • M. Tvaronavičienė, “Insights into global trends of capital flows’ peculiarities: Emerging leadership of China,” Adm. si Manag. Public, vol. 2019, no. 32, pp. 6–17, 2019, doi: 10.24818/amp/2019.32-01.

  • A. Larrabee Sønderlund, E. Hughes, and J. Smith, “The efficacy of learning analytics interventions in higher education: A systematic review,” Br. J. Educ. Technol., vol. 50, no. 5, pp. 2594–2618, 2019, doi: 10.1111/bjet.12720.

  • J. Liu, “Construction of Intelligent Library Service System from the Perspective of Artificial Intelligence,” Int. J. Front. Sociol., vol. 3, no. 1, pp. 44–51, 2021, doi: 10.25236/ijfs.2021.030106.

  • A. Shahzad, R. Hassan, A. Y. Aremu, A. Hussain, and R. N. Lodhi, “Effects of COVID-19 in E-learning on higher education institution students: the group comparison between male and female,” Qual. Quant., vol. 55, no. 3, pp. 805–826, 2021, doi: 10.1007/s11135-020-01028-z.

  • X. Xie, K. Siau, and F. F. H. Nah, “COVID-19 pandemic–online education in the new normal and the next normal,” J. Inf. Technol. Case Appl. Res., vol. 22, no. 3, pp. 175–187, 2020, doi: 10.1080/15228053.2020.1824884.

  • G. Dulac-Arnold et al., Challenges of real-world reinforcement learning: definitions, benchmarks and analysis, vol. 110, no. 9. Springer US, 2021.

  • J. Oh et al., “Discovering reinforcement learning algorithms,” Adv. Neural Inf. Process. Syst., vol. 2020-Decem, no. NeurIPS, 2020.

  • B. Daniel, “Big Data and analytics in higher education: Opportunities and challenges,” Br. J. Educ. Technol., vol. 46, no. 5, pp. 904–920, 2015, doi: 10.1111/bjet.12230.

  • M. T. J. Spaan, “Partially observable markov decision processes,” Adapt. Learn. Optim., vol. 12, pp. 387–414, 2012, doi: 10.1007/978-3-642-27645-3_12.

  • A. Koppel, G. Warnell, E. Stump, P. Stone, and A. Ribeiro, “Policy evaluation in continuous mdps with efficient kernelized gradient temporal difference,” IEEE Trans. Automat. Contr., vol. 66, no. 4, pp. 1856–1863, 2021, doi: 10.1109/TAC.2020.3029315.

  • L. C. Garaffa, M. Basso, A. A. Konzen, and E. P. de Freitas, “Reinforcement Learning for Mobile Robotics Exploration: A Survey,” IEEE Trans. Neural Networks Learn. Syst., pp. 1–15, 2021, doi: 10.1109/TNNLS.2021.3124466.


Abstract Views: 138

PDF Views: 77




  • Reinforcement Learning in Education 4.0: Open Applications and Deployment Challenges

Abstract Views: 138  |  PDF Views: 77

Authors

Delali Kwasi Dake
Department of ICT Education, University of Education, Winneba, Ghana

Abstract


Education 4.0 involves adopting technology in teaching and learning to drive innovation and growth across academic institutions. Artificial Intelligence and Machine Learning are frontrunners in Education 4.0, having already impacted diverse sectors globally. Since the COVID-19 pandemic, the conventional method of teaching and learning has become unpopular among institutions and is currently being replaced with intelligent educational data pattern identification and online learning. The teacher-centred pedagogical paradigm has significantly shifted to a learner-centred pedagogy with the emergence of Education 4.0. Reinforcement Learning has been deployed successfully in diverse sectors, and the educational domain should not be an exemption. This survey discusses Reinforcement Learning, a feedback-based machine learning technique, with application modules in the academic field. Each module is analysed for the state-action-reward implementation policies with relevant features that define individual use cases. The survey primarily examined the classroom, admission, e-learning, library and game development modules. In addition, the survey heightened the foreseeable challenges in the real-world deployment of Reinforcement Learning in educational institutions.

Keywords


Education 4.0, Reinforcement Learning, Smart Campus, Intelligent Objects, Artificial Intelligence, Machine Learning.

References