PARRoT: Predictive Ad-hoc Routing Fueled by Reinforcement Learning and Trajectory Knowledge.
Benjamin SliwaCedrik SchülerManuel PatchouChristian WietfeldPublished in: VTC Spring (2021)
Keyphrases
- reinforcement learning
- knowledge base
- knowledge acquisition
- knowledge extraction
- prior knowledge
- state space
- knowledge management
- network topologies
- domain knowledge
- knowledge representation
- learning algorithm
- learning systems
- domain experts
- markov decision processes
- knowledge sources
- network topology
- knowledge transfer
- expert systems