Application of Reinforcement Learning Techniques in Software Testing of Android Applications: A Systematic Literature Review
Year: 2025
Type: review
Study design: Systematic Review
Abstract: Software testing is a critical process in ensuring the quality and reliability of applications before they are deployed to production. However, it is resource-intensive and often tedious, particularly in the context of Android applications, which pose unique challenges due to their vast state space, diverse user interactions, and variable behaviors. Reinforcement learning (RL), a machine learning framework where agents interact with environments to improve decision-making policies, has gained attention for its potential in software testing. This systematic literature review examines the application of reinforcement learning in software testing of Android applications, focusing on widely researched areas, prevalent techniques, and emerging trends. The review analyzes 22 selected studies from an initial pool of over 30,000 articles published between 2020 and 2024. The findings highlight that automated testing is the primary focus in this domain, with Q-learning emerging as the dominant RL technique. Actor-critic methods, deep Q-networks (DQN), and policy gradient approaches are also explored in several studies, aiming to improve the adaptability and efficiency of testing processes. Most research emphasizes fault detection and coverage maximization, often targeting event-driven interactions and GUI-based behaviors. Despite significant advancements, the study identifies underexplored areas, such as test case prioritization and the integration of user behavior or user interaction data, as promising directions for future research. This review contributes to understanding the current landscape and offers guidance for future RL-based Android application testing investigations.
Authors: Nadiah Mohd Hanim, Johanna Ahmad, Mohd Arfian Ismail, Nor Amalina Mohd Sabri, Shahdatunnaim Azmi
Language: English
Subfield: Software
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410196080