RSS-Based UAV-BS 3-D Mobility Management via Policy Gradient Deep Reinforcement Learning.
Mohammad Ghadir KhoshkholghHalim YanikomerogluPublished in: CoRR (2021)
Keyphrases
- policy gradient
- mobility management
- reinforcement learning
- actor critic
- function approximation
- reinforcement learning algorithms
- base station
- energy efficient
- mobile users
- multimedia services
- policy gradient methods
- optimal control
- data dissemination
- cellular networks
- gradient method
- mobile objects
- wireless sensor networks
- context aware
- reinforcement learning methods
- model free
- state space
- function approximators
- ip networks
- path planning
- wireless technologies
- temporal difference
- heterogeneous networks
- variance reduction
- wireless mesh networks
- machine learning
- sensor networks
- single agent
- markov decision processes
- approximation methods
- optimal policy
- state action
- wireless networks
- dynamic programming
- learning process
- dynamic environments
- mobile nodes
- neural network
- mobile devices
- multi agent
- ad hoc networks