Skip to content

killianvervelle/Reinforcement_Learning_for_Software_Quality_Assurance

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

44 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement_Learning_for_Software_Quality_Assurance

This repository contains the source code for reinforcement learning assisted performance testing frameworks. Each framework enables efficient generation of performance test cases to meet specific testing objectives without requiring access to the source code or models of the system under test (SUT). It achieves this through three major components: SaFReL (Q-learning), RELOAD (DQN), A2C and PPO.

Core Frameworks

  • SaFReL: Focuses on platform-based test condition generation using self-adaptive fuzzy reinforcement learning.
  • RELOAD: Specializes in workload-based test condition generation using adaptive reinforcement learning.
  • A2C (Advantage Actor-Critic): Implements the Advantage Actor-Critic algorithm to optimize resource configurations for stress testing.
  • PPO (Proximal Policy Optimization): Implements the PPO algorithm to optimize resource configurations for stress testing.

All four enable efficient stress testing by learning optimal resource allocation policies, which can be reused in future testing scenarios. They adapt to varying resource constraints, offering a cost-effective and intelligent solution for continuous testing activities, such as system resilience testing under extreme conditions and performance evaluation under stress.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published