Uncrewed Aerial Vehicles (UAVs), commonly known as drones, have significantly advanced wireless communication frameworks by enabling the formation of Flying Ad-Hoc Networks (FANETs). FANETs facilitate autonomous collaboration among UAVs through decentralized and self-organizing communication protocols, proving especially effective in dynamic applications such as military surveillance, disaster management, and environmental monitoring. Nevertheless, traditional routing algorithms, initially developed for terrestrial networks, often fail to meet the unique challenges of FANETs, notably their high mobility and frequently changing network topologies. A framework was proposed to address these challenges; this paper formulates a multi-objective optimization problem aimed at optimizing UAV trajectories, enhancing energy efficiency, and maximizing communication range to improve overall data forwarding performance. A Reinforcement Learning (RL)-based agent is created that constantly enhances its decision-making capacity by utilizing real-time feedback and dynamically chooses best forwarding tactics. This work also combines developments in large-scale data collecting from Wireless Sensor Networks (WSNs), using mobile sinks supported by FANETs in conjunction with multi-objective optimization approaches to improve data collecting efficiency greatly. Experimental tests show that the suggested RL-based techniques outperform conventional routing protocols by properly lowering delays and raising the Packet Delivery Ratio (PDR). Moreover, simulation findings show the better scalability and adaptability of RL-enabled UAV networks, stressing its possible use in dynamic real-world situations such as disaster relief operations and environmental monitoring tasks.