Book Image

Reinforcement Learning with TensorFlow

By : Sayon Dutta
Book Image

Reinforcement Learning with TensorFlow

By: Sayon Dutta

Overview of this book

Reinforcement learning (RL) allows you to develop smart, quick and self-learning systems in your business surroundings. It's an effective method for training learning agents and solving a variety of problems in Artificial Intelligence - from games, self-driving cars and robots, to enterprise applications such as data center energy saving (cooling data centers) and smart warehousing solutions. The book covers major advancements and successes achieved in deep reinforcement learning by synergizing deep neural network architectures with reinforcement learning. You'll also be introduced to the concept of reinforcement learning, its advantages and the reasons why it's gaining so much popularity. You'll explore MDPs, Monte Carlo tree searches, dynamic programming such as policy and value iteration, and temporal difference learning such as Q-learning and SARSA. You will use TensorFlow and OpenAI Gym to build simple neural network models that learn from their own actions. You will also see how reinforcement learning algorithms play a role in games, image processing and NLP. By the end of this book, you will have gained a firm understanding of what reinforcement learning is and understand how to put your knowledge to practical use by leveraging the power of TensorFlow and OpenAI Gym.
Table of Contents (21 chapters)
Title Page
Packt Upsell
Contributors
Preface
Index

What is Go?


The game of Go originated in China around 3000 years ago. The rules of the game are simple as follows:

  • Go is a two player game
  • The default board size is 19x19 lines
  • One player places a black stone, while the other player places a white stone
  • The goal is to surround the opponent's stones and cover most of the empty spaces on the board

The following is a default board size, which is of 19x19 lines:

19x19 Go board

Even with those simple rules, the game of Go is highly complex. There are around 2.08 x 10170 possible moves in a 19x19 Go compared to 1080 atoms in universe and 10120 possible moves in chess. Thus, the intellectual depth required to play the game of Go has captured human imagination for ages. 

Go versus chess

In 1997, IBM's DeepBlue defeated the then world champion Gary Kasparov in the game of chess. Almost two decades later, Google DeepMind's AI program AlphaGo defeated the 9-dan Go player and former world champion Lee Sedol. In order to understand the giant leap and achievement...