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


We knew that reinforcement learning optimizes the reward for an agent in the environment, and the Markov decision process (MDP) is a type of environment representation and mathematical framework for modeling the decisions using states, actions, and rewards. In this chapter, we understood that Q-learning is an approach that finds the optimal action selection policy for any MDP without any transition models. On the other hand, value iteration finds the optimal action selection policy for any MDP if a transition model is given.

We also learned another important topic called the deep-Q network, which is a modified Q-learning approach that takes a deep neural network as a function approximator to generalize across different environments, unlike a Q-table, which is environment specific. Moreover, we also learnt to implement Q-learning, deep Q-networks, and SARSA algorithms in OpenAI gym environments. Most of the implementation shown previously might work better with better hyperparameter...