Reinforcement Learning: With Open AI, TensorFlow and Keras Using Python

© Abhishek Nandy and Manisha Biswas  2018

Abhishek Nandy and Manisha BiswasReinforcement Learning https://doi.org/10.1007/978-1-4842-3285-9_2

2. RL Theory and Algorithms

Abhishek Nandy¹  and Manisha Biswas²

(1)

Rm HIG L-2/4, Bldg Swaranika Co-Opt HSG, Kolkata, West Bengal, India

(2)

North 24 Parganas, West Bengal, India

 

This chapter covers how Reinforcement Learning works and explains the concepts behind it, including the different algorithms that form the basis of Reinforcement Learning.

The chapter explains these algorithms, but to start with, you will learn why Reinforcement Learning can be hard and see some different scenarios. The chapter also covers different ways that Reinforcement Learning can be implemented.

Along the way, the chapter formulates ...