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