Urbanization and population growth have increased waste, creating an excellent challenge for waste management systems. In response to these challenges, this study investigates using Reinforcement Learning (RL) algorithms to optimize waste management in urban environments. The primary purpose of this study is to solve the problem of changing the waste collection process, which is essential in reducing operating costs and increasing overall profit, with the effects of waste management. The use of Q-learning, a reinforcement learning algorithm, forms the basis of our approach. Q-learning was chosen for its performance in handling arbitrary decisions and its ability to make weak decisions, perfectly adapting to the complexities and differences in the garbage collection period. Extensive testing and analysis demonstrate the effectiveness of the proposed support learning-based waste management optimization model. This research aims to use innovative technology to improve how we plan waste collection on the fly, making waste management more efficient and cost-effective.