Dynamic robust power allocation games under channel uncertainty and time delays

Authors:
Hamidou Tembine;Abdellatif Kobbane;Mohamed El koutbi
Affiliations:
Ecole Supérieure d'Electricité 3, rue Joliot-Curie, 91192 Gif Sur Yvette Cedex, France;Mohammed V-Souissi University, ENSIAS, Rabat, Morocco;Mohammed V-Souissi University, ENSIAS, Rabat, Morocco
Venue:
Computer Communications
Year:
2011

Citing 7
Cited 0

Elements of information theory

Elements of information theory
Stochastic approximation with two time scales

Systems & Control Letters
Robust game theory

Mathematical Programming: Series A and B
Evolutionary games in wireless networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics - Special issue on game theory
Practical algorithms for a family of waterfilling solutions

IEEE Transactions on Signal Processing
Iterative water-filling for Gaussian vector multiple-access channels

IEEE Transactions on Information Theory
Dynamic Robust Games in MIMO Systems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.24

Visualization

Abstract

In this paper, we study dynamic robust power allocation strategies under the imperfectness of the channel state information at the transmitters. Considering unknown payoff functions at the transmitters, we propose an heterogeneous Delayed COmbined fully DIstributed Payoff and Strategy Reinforcement Learning (Delayed-CODIPAS-RL) in which each transmitter learns its payoff function as well as its associated optimal strategies in the long-term. We show that equilibrium power allocations can be obtained using the multiplicative weighted imitative CODIPAS-RLs and Bush-Mosteller based CODIPAS-RL. We also show almost sure convergence to the set of global optima for specific scenarios.