Anomaly Detection Under Controlled Sensing Using Actor-Critic Reinforcement Learning.
Geethu JosephMustafa Cenk GursoyPramod K. VarshneyPublished in: SPAWC (2020)
Keyphrases
- anomaly detection
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- intrusion detection
- function approximation
- neuro fuzzy
- detecting anomalies
- policy iteration
- gradient method
- markov decision processes
- state space
- intrusion detection system
- unsupervised learning
- detect anomalies
- rl algorithms
- one class support vector machines
- average reward
- multi agent
- function approximators
- adaptive control
- temporal difference learning
- transfer learning
- dynamic programming
- high dimensional
- machine learning