Reinforcement Learning in Education: A Systematic Literature Review
Saved in:
| Title: | Reinforcement Learning in Education: A Systematic Literature Review |
|---|---|
| Language: | English |
| Authors: | Anna Riedmann (ORCID |
| Source: | International Journal of Artificial Intelligence in Education. 2025 35(5):2669-2723. |
| Availability: | Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/ |
| Peer Reviewed: | Y |
| Page Count: | 55 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Information Analyses Reports - Research |
| Descriptors: | Reinforcement, Learning Processes, Artificial Intelligence, Natural Language Processing, Intervention, Evaluation Methods, Algorithms, Best Practices, Program Implementation, Technology Uses in Education |
| DOI: | 10.1007/s40593-025-00494-6 |
| ISSN: | 1560-4292 1560-4306 |
| Abstract: | We conducted a systematic literature review to examine the current research on the application of Reinforcement Learning (RL) in education. RL is a type of Machine Learning that trains an agent to take actions in an environment in order to maximize a reward signal. In recent years, researchers have explored the potential of RL for improving educational outcomes and developing personalized interventions. This systematic review (according to the PRISMA standard) surveys and evaluates 89 manuscripts from three databases (IEEE Xplore, Google Scholar, and ACM) published between 2000 and 2024 with predefined eligibility criteria. We examined the following objectives: (1) Educational contexts and evaluation strategies in RL-based educational applications, (2) impact and significance of RL-based applications for cognitive and affective variables, (3) RL algorithms and baselines used in the context of RL in education, (4) adaptation mechanisms in RL-based education, and (5) best practices for implementing RL in education. Our results suggest that RL has shown promise for a range of educational applications, such as enhancing learning outcomes or promoting student engagement. However, there are currently significant challenges and limitations to the use of RL in education, including methodological issues, and the need for broader and more large-scale deployments and evaluations with actual users relative to only using simulated data. Overall, this review provides a comprehensive overview of the current state of research on the application of RL in education and identifies areas where further research is needed to fully realize its potential as a tool for enhancing teaching and learning. Additionally, we present a set of best practices for the field, distilling key insights from our systematic review for practical application. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1500069 |
| Database: | ERIC |
| Abstract: | We conducted a systematic literature review to examine the current research on the application of Reinforcement Learning (RL) in education. RL is a type of Machine Learning that trains an agent to take actions in an environment in order to maximize a reward signal. In recent years, researchers have explored the potential of RL for improving educational outcomes and developing personalized interventions. This systematic review (according to the PRISMA standard) surveys and evaluates 89 manuscripts from three databases (IEEE Xplore, Google Scholar, and ACM) published between 2000 and 2024 with predefined eligibility criteria. We examined the following objectives: (1) Educational contexts and evaluation strategies in RL-based educational applications, (2) impact and significance of RL-based applications for cognitive and affective variables, (3) RL algorithms and baselines used in the context of RL in education, (4) adaptation mechanisms in RL-based education, and (5) best practices for implementing RL in education. Our results suggest that RL has shown promise for a range of educational applications, such as enhancing learning outcomes or promoting student engagement. However, there are currently significant challenges and limitations to the use of RL in education, including methodological issues, and the need for broader and more large-scale deployments and evaluations with actual users relative to only using simulated data. Overall, this review provides a comprehensive overview of the current state of research on the application of RL in education and identifies areas where further research is needed to fully realize its potential as a tool for enhancing teaching and learning. Additionally, we present a set of best practices for the field, distilling key insights from our systematic review for practical application. |
|---|---|
| ISSN: | 1560-4292 1560-4306 |
| DOI: | 10.1007/s40593-025-00494-6 |
