Delay-aware TDMA Scheduling with Deep Reinforcement Learning in Tactical MANET.
Gwangjin WiSunghwa SonKyung-Joon ParkPublished in: ICTC (2020)
Keyphrases
- reinforcement learning
- ad hoc networks
- end to end delay
- critical path
- mobile ad hoc networks
- routing protocol
- scheduling problem
- multi hop
- multipath routing
- function approximation
- state space
- network topology
- packet scheduling
- route discovery
- scheduling algorithm
- quality of service
- reinforcement learning algorithms
- machine learning
- learning algorithm
- end to end
- temporal difference
- resource constraints
- markov decision processes
- routing algorithm
- optimal control
- peer to peer
- optimal policy
- cross layer
- cooperative
- communication delays
- packet delivery
- mac layer
- fully distributed
- wireless networks
- mobile networks
- network connectivity
- mobile nodes
- mobile users
- resource allocation
- model free
- energy efficient