The use of reinforcement learning for autonomous spectrum allocation in 6G networks is described in this technical abstract. A type of machine learning called reinforcement learning (RL) lets agents learn policies in changing environments. When applied to autonomous spectrum allocation, RL makes it possible to select operating points that are less than optimal, ensuring system stability and increasing energy efficiency. The proposed RL-put together procedures center with respect to joint asset distribution and mental impedance the executives, to advance organization execution. Depending on the size of the spectrum resources shared by multiple users, the channels are dynamically allocated. The proposed calculations are assessed utilizing the two reproductions and genuine world test beds. Subsequently, RL-based independent range assignment can be a proficient way for 6G organizations to arrive at their maximum capacity.