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

AlphaGo – mastering Go


Traditional AI approaches based on search trees covering all possible position fail in the case of Go. The reason being the enormously huge search space because of 2.08 x 10170 possible moves and thereby, the difficulty in evaluating the strength of each possible board position. Thus, the traditional brute force approaches fail for the enormous search space of Go.

Therefore, advanced tree search such as Monte Carlo Tree Search with Deep Neural Networks was considered to be the novel approach to capture the intuition that humans use to play the game of Go. These neural networks are convolutional neural networks (CNNs) and take an image of the board, that is, the description of the board and activates it through the series of layers to find the best move as per the given state of the game. 

There are two neural networks used in the architecture of AlphaGo, which are:

  • Policy network: This neural network decides what next move/action to take
  • Value network: This neural network...