The field of wireless networks is moving towards more efficient and reliable communication systems, with a focus on underwater and mmWave networks. Researchers are exploring new approaches to address the challenges posed by these environments, such as limited energy supply, harsh communication conditions, and unexpected node malfunctions. The use of deep reinforcement learning and multi-agent reinforcement learning is becoming increasingly popular in this field, as it allows for decentralized and adaptive decision-making. Noteworthy papers in this area include: Achieving Fair-Effective Communications and Robustness in Underwater Acoustic Sensor Networks, which proposes a semi-cooperative approach to achieve fair-effective communication and robustness in imperfect and energy-constrained underwater acoustic sensor networks. Joint Scheduling and Resource Allocation in mmWave IAB Networks Using Deep RL, which presents a novel Deep Reinforcement Learning framework for joint link scheduling and resource slicing in dynamic, interference-prone IAB networks.