Automating post-exploitation with deep reinforcement learning.
Ryusei MaedaMamoru MimuraPublished in: Comput. Secur. (2021)
Keyphrases
- reinforcement learning
- function approximation
- exploration exploitation tradeoff
- model free
- reinforcement learning algorithms
- state space
- machine learning
- control problems
- robotic control
- temporal difference
- markov decision processes
- multi agent reinforcement learning
- continuous state
- optimal policy
- artificial neural networks
- learning algorithm
- information retrieval
- real world
- database
- active learning
- learning process
- deep learning
- learning agent
- transition model
- data mining