Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges and Tabular Q-Learning.
Fabio Massimo ZennaroLaszlo ErdodiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- penetration testing
- reinforcement learning algorithms
- model free
- state space
- multi agent
- temporal difference learning
- learning algorithm
- multi agent reinforcement learning
- action selection
- reinforcement learning methods
- stochastic approximation
- continuous state and action spaces
- optimal policy
- security vulnerabilities
- markov decision processes
- management practices