Brief Introduction to Deep Reinforcement Learning
The goal of this article is to give a short introduction about where Reinforcement Learning is placed in the area of AI. What it is and how it works on a basic level, as well as what current achievements and real world applications are.
Artificial intelligence is composed of many different areas. These include expert systems, logic, robotics, computer vision, natural language processing and machine learning. Reinforcement learning is a sub-area of machine learning that deals with problems of optimal decision making in a given time frame. Many such problems can be found in different areas of science and engineering.
In the field of machine learning, reinforcement learning lies between the two further areas of supervised learning and unsupervised learning. Supervised learning requires processed data sets, for which correct answers or solutions have already been given by a supervisor. In this case the algorithm learns to interpret and classify the data correctly.
Unsupervised learning, on the other hand, does not have pre-labeled data by a supervisor. The goal is to identify interrelationships from the data and thus derive and generalize…
