Reinforcement Learning with MATLAB: Understanding Rewards and Policy Structures

Recent news coverage has highlighted how computer programs trained with reinforcement learning are now beating human players in board and video games. Reinforcement learning is a type of machine learning that enables the use of artificial intelligence in complex applications from video games to robotics, self-driving cars, and more.

If you’re interested in using reinforcement learning technology for your project, but you’ve never used it before, where do you begin?

This ebook, the second of a series of three, helps you get started with reinforcement learning in MATLAB^® and Simulink^® by explaining the terminology and providing access to examples, tutorials, and trial software.

Read this ebook to learn about:

• Exploration vs. exploitation
• Rewards and proper reward formulation
• Policies and policy representations
• Neural networks in reinforcement learning