Dynamic Time Window based Reward for Reinforcement Learning in Continuous Integration Testing.
Chaoyue PanYang YangZheng LiJunxia GuoPublished in: Internetware (2020)
Keyphrases
- reinforcement learning
- integration testing
- state space
- function approximation
- action space
- reward function
- object oriented programs
- dynamic environments
- optimal control
- reinforcement learning algorithms
- model free
- markov decision processes
- machine learning
- black box
- temporal difference
- open source
- dynamic programming
- eligibility traces
- multi agent
- information technology
- specification languages
- component based software