ADRL: A Hybrid Anomaly-Aware Deep Reinforcement Learning-Based Resource Scaling in Clouds.
Sara Kardani-MoghaddamRajkumar BuyyaKotagiri RamamohanaraoPublished in: IEEE Trans. Parallel Distributed Syst. (2021)
Keyphrases
- reinforcement learning
- function approximation
- anomaly detection
- reinforcement learning algorithms
- model free
- resource allocation
- state space
- machine learning
- cloud computing
- intrusion detection
- markov decision processes
- resource management
- action selection
- temporal difference
- resource selection
- data management
- hidden markov models
- learning environment
- metadata
- learning algorithm
- database
- temporal difference learning
- multi agent reinforcement learning
- robotic control