Resource Allocation in Wireless Control Systems via Deep Policy Gradient.
Vinicius Lima SilvaMark EisenKonstantinos GatsisAlejandro RibeiroPublished in: SPAWC (2020)
Keyphrases
- resource allocation
- policy gradient
- control system
- reinforcement learning
- wireless networks
- function approximation
- optimal control
- resource allocation problems
- wireless communication
- gradient method
- reinforcement learning algorithms
- game theory
- resource management
- approximation methods
- allocation problems
- reinforcement learning methods
- single agent
- resource allocation decisions
- scarce resources
- variance reduction
- partially observable markov decision processes
- real time
- state space
- multi agent systems
- control strategy
- optimal solution
- special case
- dynamic programming
- optimal policy