Service Function Chaining in NFV-Enabled Edge Networks with Natural Actor-Critic Deep Reinforcement Learning.
Ruijie WangJunhuai LiKan WangXuan LiuXuan LitPublished in: ICCC (2021)
Keyphrases
- natural actor critic
- reinforcement learning
- robot arm
- function approximators
- function approximation
- policy gradient methods
- reinforcement learning problems
- reinforcement learning methods
- multi agent
- state space
- model free
- machine learning
- reinforcement learning algorithms
- policy gradient
- control policy
- markov decision processes
- optimal policy
- learning algorithm