Optimal Query Execution Plan with Deep Reinforcement Learning

Umar Jamshid

Abstract

We examine the use of profound support learning for inquiry development. The technique is to
gradually construct queries by encoding features of sub-inquiries using a learnt representation. We
specifically focus on the organization of the state progress effort and the state portrayal issue. We
provide preliminary results and investigate how we might use the state representation to further
refine question streamlining using assist learning