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

Deep Q-networks

If we recall Chapter 2Training Reinforcement Learning Agents Using OpenAI Gym, where we tried to implement a basic Q-network, we studied that for a real-world problem, Q-learning using a Q-table is not a feasible solution owing to continuous state and action spaces. Moreover, a Q-table is environment-specific and not generalized. Therefore, we need a model which can map the state information provided as input to Q-values of the possible set of actions. This is where a neural network comes to play the role of a function approximator, which can take state information input in the form of a vector, and learn to map them to Q-values for all possible actions.

Let's discuss the issues with Q-learning in a gaming environment and evolution of deep Q-networks. Consider applying Q-learning to a gaming environment, the state would be defined by the location of the player, obstacles, opponents, and so on, but this would be game-specific and cannot be generalized over other gaming environments...