Mobile robots, as intelligent technological products that replace humans in various tasks, have not only brought significant convenience to humans but also provided support for the of scientific and technological achievements. Among mobile robots, path planning is a hot topic of research. How to enable mobile robots to adapt to complex dynamic environments and effective path planning is the current research focus and the significance of conducting research. Therefore, this paper uses literature research methods to explain the current research background and introduce the domestic and international research status. Meanwhile, it outlines the basic theories, introduces the theories of deep learning and reinforcement learning, as well as related algorithms of deep reinforcement, to provide a theoretical basis for the research. Finally, through simulation experiments, the application of path planning algorithms for mobile robots based on deep reinforcement learning in complex dynamic environments is analyzed, providing reference and inspiration for related research.