Distributed correlated Q-learning for dynamic transmission control of sensor networks

This paper considers a Markovian dynamical game theoretic setting for distributed transmission control in a wireless sensor network. The available spectrum bandwidth is modeled as a Markov chain. A distributed algorithm named correlated Q-learning algorithm is proposed to obtain the correlated equilibrium policies of the system. This algorithm has the decentralized feature and is easily implementable in a real system. Numerical example is also provided to verify the performances of the proposed algorithms.