International Journal of Advanced Research in Computer and Communication Engineering

A monthly peer-reviewed online and print journal

ISSN Online 2278-1021
ISSN Print 2319-5940

Abstract: Reinforcement learning is used to automatically determine the ideal behaviour of a machine with the help of machine learning algorithms to maximize the performance of the machine. Explicit goals are not given to the algorithm. They have to learn this optimal goal by trial and error .think of game contra in which the movement of the player which is done by clicking the buttons that decide the result of the optimal gameplay, by pressing the button the error occurs and the reward are given accordingly. A formula is used to determine the reward of the machine and according to it, the rewards are given from which the machine learns. The rewards can be positive or they can be negative and on the basis of rewards, the machine’s accuracy is denoted.

Keywords: Reinforcement learning, RL, base of AI, machine language, machine accuracy


PDF | DOI: 10.17148/IJARCCE.2018.776