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

Reinforcement learning


In this experiment of algorithmic portfolio management, the portfolio managing agent performs the trading actions in the financial market environment powered by reinforcement learning. The environment comprises all the available assets of the given market. Since the environment is large and complex, it's impossible for the agent to fully observe the state, that is, to get all the information of the state. Moreover, since the full order history of the market is too huge to process, sub-sampling from the order history data simplifies the processing of state representation of the environment. These sub-sampling methods include:

  • Periodic feature extraction: Discretizes the time into many periods and then extracts the opening, highest, lowest, and closing prices for each of those periods
  • Data slicing: Consider only the data from recent time periods and avoid the older historical data in order to do current state representation of the environment

The agent made some buying...