A Mutual Information-Based Assessment of Reverse Engineering on Rewards of Reinforcement Learning.
Tong ChenJiqiang LiuThar BakerYalun WuYingxiao XiangYike LiWenjia NiuEndong TongAlbert Y. ZomayaPublished in: IEEE Trans. Artif. Intell. (2023)
Keyphrases
- reverse engineering
- reinforcement learning
- software engineering
- markov decision processes
- function approximation
- dynamic analysis
- image registration
- software maintenance
- state space
- gene regulatory networks
- reinforcement learning algorithms
- object oriented
- optimal policy
- software product
- business rules
- program understanding
- computer aided design
- reverse engineer
- conceptual schema
- learning algorithm
- reward shaping
- reward function
- software engineers
- model free
- mutual information
- software evolution
- machine learning
- control policy
- program slicing