Reinforcement Learning with TensorFlow

By : Dutta

2.2 (5)

Buy this Book

Reinforcement Learning with TensorFlow

2.2 (5)

By: Dutta

Buy this Book

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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Deep Learning – Architectures and Frameworks

Deep learning

Reinforcement learning

Introduction to TensorFlow and OpenAI Gym

The pioneers and breakthroughs in reinforcement learning

Summary

Training Reinforcement Learning Agents Using OpenAI Gym

The OpenAI Gym

Programming an agent using an OpenAI Gym environment

Summary

Markov Decision Process

Markov decision processes

Partially observable Markov decision processes

Training the FrozenLake-v0 environment using MDP

Summary

Policy Gradients

The policy optimization method

Why policy optimization methods?

Policy objective functions

Temporal difference rule

Policy gradients

Agent learning pong using policy gradients

Summary

Q-Learning and Deep Q-Networks

Why reinforcement learning?

Model based learning and model free learning

Q-learning

Deep Q-networks

The Monte Carlo tree search algorithm

The SARSA algorithm

Summary

Asynchronous Methods

Why asynchronous methods?

Asynchronous one-step Q-learning

Asynchronous one-step SARSA

Asynchronous n-step Q-learning

Asynchronous advantage actor critic

A3C for Pong-v0 in OpenAI gym

Summary

Robo Everything – Real Strategy Gaming

Real-time strategy games

Reinforcement learning and other approaches

Reinforcement learning in RTS gaming

Summary

AlphaGo – Reinforcement Learning at Its Best

What is Go?

AlphaGo – mastering Go

AlphaGo Zero

Summary

Reinforcement Learning in Autonomous Driving

Machine learning for autonomous driving

Reinforcement learning for autonomous driving

Proposed frameworks for autonomous driving

DeepTraffic – MIT simulator for autonomous driving

Summary

Financial Portfolio Management

Introduction

Problem definition

Data preparation

Reinforcement learning

Further improvements

Summary

Reinforcement Learning in Robotics

Reinforcement learning in robotics

Challenges in robot reinforcement learning

Open questions and practical challenges

Key takeaways

Summary

Deep Reinforcement Learning in Ad Tech

Computational advertising challenges and bidding strategies

Real-time bidding by reinforcement learning in display advertising

Summary

Reinforcement Learning in Image Processing

Hierarchical object detection with deep reinforcement learning

Summary

Deep Reinforcement Learning in NLP

Text summarization

Text question answering

Summary

Further topics in Reinforcement Learning

Continuous action space algorithms

Scoring mechanism in sequential models in NLP

Summary

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

2.2 (5)

5 star

20%

4 star

3 star

20%

2 star

1 star

60%

Policy Gradients

So far, we have seen how to derive implicit policies from a value function with the value-based approach. Here, an agent will try to learn the policy directly. The approach is similar, any experienced agent will change the policy after witnessing it.

Value iteration, policy iteration, and Q-learning come under the value-based approach solved by dynamic programming, while the policy optimization approach involves policy gradients and union of this knowledge along with policy iteration, giving rise to actor-critic algorithms.

As per the dynamic programming method, there are a set of self-consistent equations to satisfy the Q and V values. Policy optimization is different, where policy learning happens directly, unlike deriving from the value function: