Task scheduling on the cloud involves processing a large set of variables from both the task side and the scheduling machine side. This processing often results in a computational model that produces efficient task to machine maps. The efficiency of such models is decided based on various parameters like computational complexity, mean waiting time for the task, effectiveness to utilize the machines, etc. In this paper, a novel Q-Dynamic and Integrated Resource Scheduling (DAIRS-Q) algorithm is proposed which combines the effectiveness of DAIRS with Q-Learning in order to reduce the task waiting time, and improve the machine utilization efficiency. The DAIRS algorithm produces an initial task to machine mapping, which is optimized with the help of a reward & penalty model using Q-Learning, and a final task-machine map is obtained. The performance of the proposed algorithm showcases a 15% reduction in task waiting time, and a 20% improvement in machine utilization when compared to DAIRS and other standard task scheduling algorithms.