Multi-Agent Q-Learning for Power Allocation in Interference Channel

Signal transmission in wireless networks suffers from unwanted interference. To maximize signal to interference plus noise ratio, transmit power of each transmitter needs to be optimally allocated. Here, we propose to use multi-agent Q-learning to optimize such transmit power within interference channel. Our simulation indicated that multi-agent Q-Iearning resulted in better sum-rate than the traditional methods such as the maximum power allocation and the random power allocation. Our work offers a novel and practical computational approach to optimizing signal transmission in wireless networks.