Unlocking the Power of Reinforcement Learning: Investigating Optimal Q-Learning Parameters for Routing in Flying Ad Hoc Networks.
Mariem BousaidSafa KaabiAmine DhraiefKhalil DriraPublished in: WETICE (2023)
Keyphrases
- ad hoc networks
- reinforcement learning
- routing protocol
- routing algorithm
- network topology
- wireless ad hoc networks
- function approximation
- end to end
- dynamic programming
- reinforcement learning algorithms
- wireless networks
- state space
- mobile wireless
- qos routing
- quality of service
- mobile ad hoc networks
- mac protocol
- transmission range
- base station
- key management
- optimal policy
- peer to peer
- multi agent reinforcement learning
- model free
- multi hop
- network nodes
- learning algorithm
- end to end delay
- packet forwarding
- mobile nodes
- action selection
- power consumption
- routing scheme
- control policy
- network infrastructure
- secure routing
- average end to end delay
- multipath routing
- markov decision processes
- sensor networks
- wireless sensor networks
- wireless mesh networks
- qos parameters
- node disjoint
- multimedia
- continuous state spaces
- propagation model
- multiple paths
- topology control
- temporal difference
- response time
- pairwise
- node mobility
- digital libraries