Intelligent Tutoring System

1941 Words8 Pages
Personalized Intelligent Tutoring System using Reinforcement Learning for Autistic Student to teach Skating Jaydeep Karangia Prof. Mayura Nagar Dheeraj Pandey jaydeepkarangia91@gmail.com gujmayu@gmail.com dheerajp883@gmail.com Sardar Patel Institute of Technology Sardar Patel Institute of Technology Sardar Patel Institute of Technology Abstract— Many intelligent tutoring systems have been developed using different artificial intelligence techniques. In this paper, we propose the use of reinforcement learning for building a personalized intelligent tutoring system to teach skating to an autistic student who can't communicate well with others. We make use of personalized intelligent tutoring system…show more content…
It provides hint whenever needed, details of knowledge required to solve a problem and relations between different problem and topic. The Student Module is based on prior knowledge of student on related topic, his learning habits and environment in which training takes place. The Teaching Module represents a tutor who has the knowledge about the methods of instruction and defines a solution for a particular method. 2. RELATED LITERATURE STUDY 2.1 Overview Of Intelligent Tutoring System Intelligent Tutoring Systems (ITS) are computer-based tutors which act as a supplement to human teachers. An ITS can help to learn student and test knowledge without being controlled by a teacher. The main advantage of an ITS is that it acts according to students cognitive abilities. The classical model of ITS architecture has four main modules • Knowledge Module • Student Module • Teaching Module • User Interface Module. [3] 2.1.1 Architecture Of Intelligent Tutoring System Fig. 1 Traditional Intelligent Tutoring System [4] 2.1.1.1 The Knowledge Module…show more content…
It is the most important part of an ITS. This module is the heart of the whole system. It works with the other modules and does the entire decision making. 2.1.1.4 The User Interface Module : The User Interface is responsible for providing an environment for interaction between the system and students. 2.2 Overview Of Reinforcement Learning Reinforcement Learning is a type of Machine Learning and thereby also a branch of Artificial Intelligence. It allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance. Simple reward feedback is required for the agent to learn its behavior. In Reinforcement Learning, the agent is supposed to decide the best action to select based on his current state.[5] Fig. 2 Working of Reinforcement Learning Reinforcement Learning helps to decide what to do, how to do and how to map multiple situations to actions in order to maximize numerical signal award. The learner is not told which actions should be taken. This learning method discovers which actions yield the most reward by trying
Open Document