RESUMEN

In this study, the problem of dynamic channel access in distributed underwater acoustic sensor networks (UASNs) is considered. First, we formulate the dynamic channel access problem in UASNs as a multi-agent Markov decision process, wherein each underwater sensor is considered an agent whose objective is to maximize the total network throughput without coordinating with or exchanging messages among different underwater sensors. We then propose a distributed deep Q-learning-based algorithm that enables each underwater sensor to learn not only the behaviors (i.e., actions) of other sensors, but also the physical features (e.g., channel error probability) of its available acoustic channels, in order to maximize the network throughput. We conduct extensive numerical evaluations and verify that the performance of the proposed algorithm is similar to or even better than the performance of baseline algorithms, even when implemented in a distributed manner.