Reinforcement learning is a type of machine learning technique where a computer agent learns to perform a task through repeated trial-and-error interactions within a dynamic environment.
This ebook helps you get started with reinforcement learning by explaining the terminology and providing access to examples, tutorials, and additional resources. It covers everything you need to know, from rewards and policy structures to training and deployment.
You will learn:
- The basics of the reinforcement learning problem and how it compares to traditional control techniques
- The different types of training algorithms, including policy-based, value-based, and actor-critic methods
- The pros and cons of each training method including the Bellman equation for Q-learning
- The difference between supervised, unsupervised, and reinforcement learning
- What you should consider before deploying a trained policy, as well as overall challenges and drawbacks associated with this technique
