Reinforcement learning based predictive handover for pedestrian-aware mmWave networks.
Yusuke KodaKoji YamamotoTakayuki NishioMasahiro MorikuraPublished in: INFOCOM Workshops (2018)
Keyphrases
- reinforcement learning
- function approximation
- computer networks
- network design
- social networks
- learning algorithm
- network analysis
- complex networks
- markov decision processes
- reinforcement learning algorithms
- pedestrian detection
- state space
- neural network
- temporal difference
- connectionist networks
- cellular networks
- network size
- learning classifier systems
- mobile networks
- complex systems
- optimal policy
- dynamic programming
- multi agent
- machine learning