A Model Of Intelligent Arranging School Syllabus System Based On Reinforcement Learning

The Reinforcement learning is a machine learning framework in which an agent manipulates its environment through a series of actions, and in response to each action, receives a reward value. The agent stores its knowledge about how to choose reward maximizing actions in a mapping from agent internal states to actions.Curriculum arrangement in a university is very complex because the scope of curriculum arrangement is very wide and it deals with so many things. Although some experts in the world has investigated in how to arrange curriculum quickly and logically for a few years, there is not reasonable and applied curriculum arrangement system. I analyze the request of curriculum arrangement, using intellect learning arithmetic's Q-learning, designing an applied mathematics model to deal with this problem. I discuss theory, realization and practice of that reinforcement learning is used to arrange curriculum.The reinforcement learning arithmetic and neural network theory are introduced in this thesis briefly. I discuss how to design and realize intellect mathematics model of curriculum arrangement, expatiating feasibility, advantage and disadvantage of that reinforcement learning is used in curriculum arrangement. In fact, curriculum arrangement mathematics model based in reinforcement learning is brought forward, and program of this model had been developed. In practice, using this model, I had arranged curriculum in one term, and had analyzed its effect. As a result, this model is usable and primary in arranging curriculum automatically by computer.