الفهرس 
INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 88 |  |  |
| | | from | 88 | | |
Abstract
Machine learning is a branch of the artificial intelligence field of the computer science, which concerns the construction and study of computer systems that can learn from data, without being explicitly programmed by progressively improve performance on a specific task to making data-driven predictions or decisions. The artificial intelligence is the study of intelligent agents that perceive their environment and take actions to maximize their chance of successfully achieving their goals. The machine learning could be classified into three main types that could be described as: supervised learning (need labeled training data), unsupervised learning (used unlabeled training data), or reinforcement learning. Reinforcement learning does not need a training data; it has become an important subject nowadays.Reinforcement learning is a machine learning inspired by behaviorist psychology, concerned with how software agents ought to take actions in an environment to maximize some notion of cumulative reward. Reinforcement learning model does not need a training data set, but depending upon an agent intersection with an environment that is interpreted into next state and reward function, which are fed back into the agent and takes action to maximize its chance of success at an arbitrary goal. It has been applied successfully to various problems, including robot control, elevator scheduling, telecommunications, backgammon, and checkers. Reinforcement Learning aims to learn, through experience from trial and error, how to behave successfully to achieve a goal, while interacting with the external environment.