In the hotel sector, dynamic pricing is a significant tactic used where maximizing income while preserving ideal occupancy rates presents great difficulty. This work presents a complete Reinforcement Learning (RL) framework specifically for hotel sector real-time dynamic pricing. Unlike fixed or Rule-Based Pricing strategies, our approach lets room rates constantly change depending on changing market conditions, including consumer demand, competitor pricing, seasonal variations, and booking trends. Leveraging a dataset from Booking.com including historical price data, occupancy rates, and competitor pricing, our RL model learns to adaptively optimize pricing strategies, striking the ideal balance between revenue-maximizing and competitive pricing. The RL agent can outperform conventional pricing strategies by including external market elements in the decision-making process, obtaining higher total revenue, occupancy rates, and income per available room (RevPAR). Comprehensive analyses show how flexible the model is across several hotel types and market environments, so highlighting the advantages of machine learning in improving revenue management techniques for the hotel sector. Finally, by empowering a scalable, data-driven solution for dynamic pricing that guarantees that hotels are competitive in the face of changing markets, this study demonstrates the transforming possibilities of regeneration of RL-based systems.