The rapid evolution of mobile communication technologies has propelled mobile edge computing (MEC) as a pivotal paradigm bringing cloud capabilities and storage resources to the network edges, thereby, enabling the execution of computation-intensive, latency-sensitive applications at the network edge, and addressing limited device resources. However, efficient operation in MEC-assisted systems necessitates proper task executions onto MEC servers. Meanwhile, deep reinforcement learning (DRL) can substantially enhance the performance of MEC-enhanced networks by incorporating decision-making capabilities into individual network entities and edge servers. This paper presents a comprehensive survey of the applications of DRL in MEC ecosystems. More specifically, it explores the applications of DRL in MEC-enabled terrestrial wireless networks (TWNs) including Internet-of-things (IoT) and vehicular networks (VNs). The article provides a comprehensive roadmap for researchers navigating the complexities of intelligent systems and MEC-enabled networks, offering a meticulous understanding of the continuously evolving landscape in this domain. Beginning with foundational DRL principles, the survey scrutinizes the integration of DRL in MEC-enabled TWNs, showcasing its efficacy in optimizing modern TWNs. In the context of MEC-empowered IoT, the paper highlights the role of DRL in enhancing resource allocation, data management, and scalability enhancements. Extending beyond, the paper discusses MEC-enabled VNs, where DRL transforms its role in traffic signal control, and route optimization, ultimately improving efficiency and safety. Additionally, we highlight significant challenges and outline future research directions in applying DRL in terrestrial networks (TWNs) empowered by the MEC paradigm.