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

Reinforcement learning in RTS gaming

Here we will discuss how reinforcement learning algorithms can be implemented to solve the real-time strategy gaming problem. Let's recall the basic components of reinforcement learning again, they are are follows:

  • States S
  • Actions A
  • Rewards R
  • Transition model (if on-policy, not required for off-policy learning)

If these components are perceived and processed by the sensors present on the learning agent while receiving signals from the given gaming environment, then a reinforcement learning algorithm can be successfully applied. The signals perceived by the sensors can be processed to form the current environment state, predict the action as per the state information, and receive feedback, that is, reward where the action taken was good or bad. This updates that state-action pair value that is, reinforces its learning as per the feedback received.

Moreover, the higher dimension state and action spaces can be encoded to compact lower dimensions by using deep...