Modelling penetration testing with reinforcement learning using capture-the-flag challenges: Trade-offs between model-free learning and a priori knowledge.
Fabio Massimo ZennaroLászló ErdodiPublished in: IET Inf. Secur. (2023)
Keyphrases
- reinforcement learning
- model free
- trade off
- learning process
- learning algorithm
- reinforcement learning algorithms
- function approximation
- state space
- supervised learning
- learning problems
- reinforcement learning methods
- rl algorithms
- temporal difference learning
- temporal difference
- learning tasks
- markov decision processes
- function approximators
- active learning
- hardware and software
- optimal control
- intrusion detection
- unsupervised learning
- security analysis
- stochastic games
- machine learning
- data mining