A Distributed Average Cost Reinforcement Learning approach for Power Control in Wireless 5G Networks.
Antonio OrnatelliAlessandro GiuseppiAndrea TortorelliPublished in: AIIoT (2022)
Keyphrases
- power control
- average cost
- markov decision processes
- reinforcement learning
- resource management
- optimal policy
- wireless mesh networks
- energy efficient
- multi hop
- power consumption
- wireless networks
- cellular networks
- optimal control
- cognitive radio
- long run
- computer networks
- infinite horizon
- finite state
- power management
- control policy
- multi agent
- markov decision process
- markov decision chains
- medium access control
- wireless sensor networks
- wireless communication
- state space
- learning algorithm
- finite number
- energy consumption
- social networks
- multistage
- resource allocation
- mobile ad hoc networks
- wifi
- network structure
- intelligent agents
- end to end
- dynamic programming
- real time
- linear program
- routing algorithm
- mobile nodes
- linear programming
- sensor networks
- management system
- mobile devices
- total cost