Distributed learning of equilibria for a stochastic game on interference channels

We consider a wireless communication system in which N transmitter-receiver pairs want to communicate with each other. Each transmitter transmits data at a certain rate using a power that depends on the channel gain to its receiver. If a receiver can successfully receive the message, it sends an acknowledgement (ACK), else it sends a negative ACK (NACK). Each user aims to maximize its probability of successful transmission. We formulate this problem as a stochastic game and propose a fully distributed learning algorithm to find a correlated equilibrium (CE). We also propose a fully distributed learning algorithm to find a Pareto optimal solution, and we compare the utilities of each user at the CE and the Pareto point and also with some other well known recent algorithms.