DeepPR: Progressive Recovery for Interdependent VNFs With Deep Reinforcement Learning.
Genya IshigakiSiddartha DevicRiti GourJason P. JuePublished in: IEEE J. Sel. Areas Commun. (2020)
Keyphrases
- reinforcement learning
- function approximation
- state space
- learning algorithm
- machine learning
- temporal difference
- reinforcement learning algorithms
- multi agent
- recovery algorithm
- temporal difference learning
- model free
- relational reinforcement learning
- dynamic programming
- reinforcement learning methods
- direct policy search
- image sequences
- multi agent reinforcement learning
- control policy
- function approximators
- partially observable
- radial basis function
- unsupervised learning
- information systems
- learning process
- artificial neural networks
- decision trees