Self-Optimization of Cellular Networks Using Deep Reinforcement Learning with Hybrid Action Space.
Mariam M. N. AboelwafaGhada AlsuhliKarim BanawanKarim G. SeddikPublished in: CCNC (2022)
Keyphrases
- action space
- cellular networks
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- real valued
- continuous state
- wireless networks
- action selection
- reinforcement learning methods
- mobile users
- state action
- continuous state spaces
- base station
- single agent
- markov decision process
- stochastic processes
- optimal policy
- function approximators
- multi hop
- function approximation
- supply chain management
- cost effective
- multi agent systems