Reinforcement-based data transmission in temporally-correlated fading channels: Partial CSIT scenario

Reinforcement algorithms refer to the schemes where the results of the previous trials and a reward-punishment rule are used for parameter setting in the next steps. In this paper, we use the concept of reinforcement algorithms to develop different data transmission models in wireless networks. Considering temporally-correlated fading channels, the results are presented for the cases with partial channel state information at the transmitter (CSIT). As demonstrated, the implementation of reinforcement algorithms improves the performance of communication setups remarkably, with the same feedback load/complexity as in the state-of-the-art schemes.