An online learning algorithm to play discounted repeated games in wireless networks.
Juan ParrasPatricia A. ApellánizSantiago ZazoPublished in: Eng. Appl. Artif. Intell. (2022)
Keyphrases
- wireless networks
- repeated games
- average reward
- games played
- stochastic games
- incomplete information
- markov decision processes
- wireless communication
- mobile computing
- infinite horizon
- ad hoc networks
- optimal policy
- cellular networks
- nash equilibrium
- long run
- low bandwidth
- game theoretic
- wireless technologies
- multimedia services
- cross layer
- game playing
- finite state
- dynamic programming
- network coding
- neural network
- model free
- average cost
- learning process
- wired networks
- multi agent systems