QoS Routing in MANETS with Imprecise Information Using Actor-Critic Reinforcement Learning.
Wipawee UsahaJavier A. BarriaPublished in: WCNC (2007)
Keyphrases
- actor critic
- qos routing
- imprecise information
- reinforcement learning
- mobile ad hoc networks
- ad hoc networks
- routing algorithm
- multi criteria
- routing protocol
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- network topology
- quality of service
- approximate dynamic programming
- neuro fuzzy
- gradient method
- function approximation
- policy iteration
- state space
- qos requirements
- markov decision processes
- multipath
- qos parameters
- dynamic programming
- shortest path
- average reward
- artificial intelligence
- temporal difference learning
- mobile networks
- mobile nodes
- learning algorithm
- model free
- end to end
- end to end delay
- wireless sensor networks
- markov decision process
- multi agent
- dynamical systems
- step size
- decision makers
- finite state