From media streaming and e-commerce to education and healthcare, recommendation systems are now absolutely essential in many different fields. Conventional methods including content-based filtering and collaborative filtering sometimes miss the sequential, changing character of user preferences. By simulating recommendations as sequential decisions with long-term feedback, reinforcement learning (RL) offers a strong substitute. This survey presents a thorough investigation of RL-based recommendation systems together with important frameworks including hierarchical reinforcement learning, policy-guided reasoning, and Deep Q-Networks. We provide a disciplined taxonomy contrasting these approaches by design, flexibility, and application setting. We also look at ethical issues, pragmatic deployment problems, and evaluation difficulties in actual environments. By mapping the changing terrain of RL in recommendation and pointing up future directions, this work seeks to direct practitioners as well as researchers.