More than mere computing ability, the importance of job scheduling is stressed in cloud computing to ensure the shortest possible job completion durations. Traditional techniques such as Shortest Job first are incapable of coping with the ever-changing nature of the cloud environment and generally result in poor resource utilization and longer completion times for tasks. A hybrid approach is proposed, using Q-learning, a reinforcement learning technique, and logistic regression to classify jobs in cloud environments. Contributions include dynamic job scheduling based on Q-learning, optimized resource usage, and task prioritization using regression analysis. It could be observed from experimental results that the proposed hybrid approach attains superiority in CPU, memory, and GPU efficiencies as 89.6%, 84.1%, and 77.5%, respectively; furthermore, task completion time is 57.3% when compared with conventional approaches.