Actor-critic architecture based probabilistic meta-reinforcement learning for load balancing of controllers in software defined networks.
Ashish SharmaSanjiv TokekarSunita VarmaPublished in: Autom. Softw. Eng. (2022)
Keyphrases
- load balancing
- reinforcement learning
- actor critic
- temporal difference
- dynamic load balancing
- function approximation
- approximate dynamic programming
- reinforcement learning algorithms
- policy gradient
- optimal control
- distributed systems
- policy iteration
- grid computing
- computing platform
- gradient method
- peer to peer
- model free
- neuro fuzzy
- load balancing strategy
- state space
- dynamic programming
- optimal policy
- multi agent
- mobile agents
- supervised learning
- rl algorithms
- learning problems
- markov decision processes
- function approximators
- learning algorithm
- average reward
- evaluation function
- action selection
- fixed point
- control system
- load balancing strategies
- real time
- policy gradient methods
- grid services
- control policy
- markov decision process
- control strategies
- linear program
- metadata
- machine learning