Reinforcement Learning in Education: A Literature Review

Abstract

The utilization of reinforcement learning (RL) within the field of education holds the potential to bring about a significant shift in the way students approach and engage with learning and how teachers evaluate student progress. The use of RL in education allows for personalized and adaptive learning, where the difficulty level can be adjusted based on a student’s performance. As a result, this could result in heightened levels of motivation and engagement among students. The aim of this article is to investigate the applications and techniques of RL in education and determine its potential impact on enhancing educational outcomes. It compares the various policies induced by RL with baselines and identifies four distinct RL techniques: the Markov decision process, partially observable Markov decision process, deep RL network, and Markov chain, as well as their application in education. The main focus of the article is to identify best practices for incorporating RL into educational settings to achieve effective and rewarding outcomes. To accomplish this, the article thoroughly examines the existing literature on using RL in education and its potential to advance educational technology. This work provides a thorough analysis of the various techniques and applications of RL in education to answer questions related to the effectiveness of RL in education and its future prospects. The findings of this study will provide researchers with a benchmark to compare the usefulness and effectiveness of commonly employed RL algorithms and provide direction for future research in education.

Biped Robots Control in Gusty Environments with Adaptive Exploration Based DDPG

“…The fundamental principle of reinforcement learning is that an agent determines its actions through interaction with the environment, based on the state of the environment, and by receiving rewards or punishment signals as feedback [ 26 ]. The agent’s task is to learn, through trial and error, which actions to take to maximize its cumulative reward over the long term.…”

Enhancing UAV Aerial Docking: A Hybrid Approach Combining Offline and Online Reinforcement Learning

“…The inspiration for RL comes from behavioral theories in psychology, how organisms gradually form expectations of stimuli and habitual behaviors that can obtain maximum benefits under the stimuli of rewards or punishments given by the environment. This method is universal, so it has been studied in many fields, such as education, marketing, robotics, gaming, autonomous driving, natural language processing, internet of things security, recommendation systems, finance, and energy management [45,46].…”

How artificial intelligence can fight environmental issues

“…Small change in one single environment would have not as much impact as thousands and millions of refined paths. Through optimization of processes, one can reduce unnecessary waste and force required, which in theory must have a positive influence on environment [10,11].…”