Using feedback in collaborative reinforcement learning to adaptively optimize MANET routing.
Jim DowlingEoin CurranRaymond CunninghamVinny CahillPublished in: IEEE Trans. Syst. Man Cybern. Part A (2005)
Keyphrases
- reinforcement learning
- routing protocol
- mobile ad hoc networks
- ad hoc networks
- network topology
- chat conversations
- routing algorithm
- node density
- collaborative learning
- state space
- wireless sensor networks
- wireless ad hoc networks
- function approximation
- multipath
- energy consumption
- network layer
- multi hop
- cross layer
- aodv routing protocol
- multi agent
- cooperative
- markov decision processes
- routing overhead
- relevance feedback
- machine learning
- knowledge sharing
- learning algorithm
- route discovery
- routing table
- reinforcement learning algorithms
- routing problem
- optimal policy
- dynamic programming
- mobile nodes
- learning process
- multi agent systems
- end to end delay
- action selection
- routing scheme
- energy efficient
- sensor networks
- peer to peer