Master reinforcement learning, a popular area of machine learning, starting with the basics: discover how agents and the environment evolve and then gain a clear picture of how they are inter-related. You'll then work with theories related to reinforcement learning and see the concepts that build up the reinforcement learning process.
Reinforcement Learning discusses algorithm implementations important for reinforcement learning, including Markov's Decision process and Semi Markov Decision process. The next section shows you how to get started with Open AI before looking at Open AI Gym. You'll then learn about Swarm Intelligence with Python in terms of reinforcement learning. The last part of the book starts with the TensorFlow environment and gives an outline of how reinforcement learning can be applied to TensorFlow. There's also coverage of Keras, a framework that can be used with reinforcement learning. Finally, you'll delve into Google's Deep Mind and see scenarios where reinforcement learning can be used.
What You'll Learn
Absorb the core concepts of the reinforcement learning process
Use advanced topics of deep learning and AI
Work with Open AI Gym, Open AI, and Python
Harness reinforcement learning with TensorFlow and Keras using Python
Who This Book Is For
Data scientists, machine learning and deep learning professionals, developers who want to adapt and learn reinforcement learning.
Author(s): Abhishek Nandy, Manisha Biswas
Publisher: Apress
Year: 2017
Language: English
Pages: 167
Contents
About the Authors
About the Technical Reviewer
Acknowledgments
Introduction
Chapter 1: Reinforcement Learning Basics
What Is Reinforcement Learning?
Faces of Reinforcement Learning
The Flow of Reinforcement Learning
Different Terms in Reinforcement Learning
Gamma
Lambda
Interactions with Reinforcement Learning
RL Characteristics
How Reward Works
Agents
RL Environments
Deterministic
DFA (Deterministic Finite Automata)
NDFA (Nondeterministic Finite Automaton)
Observable
Discrete or Continuous
Single Agent and Multiagent Environments
Conclusion
Chapter 2: RL Theory and Algorithms
Theoretical Basis of Reinforcement Learning
Where Reinforcement Learning Is Used
Manufacturing
Inventory Management
Delivery Management
Finance Sector
Why Is Reinforcement Learning Difficult?
Preparing the Machine
Installing Docker
An Example of Reinforcement Learning with Python
What Are Hyperparameters?
Writing the Code
What Is MDP?
The Markov Property
The Markov Chain
MDPs
SARSA
Temporal Difference Learning
How SARSA Works
Q Learning
What Is Q?
How to Use Q
SARSA Implementation in Python
The Entire Reinforcement Logic in Python
Dynamic Programming in Reinforcement Learning
Conclusion
Chapter 3: OpenAI Basics
Getting to Know OpenAI
Installing OpenAI Gym and OpenAI Universe
Working with OpenAI Gym and OpenAI
More Simulations
OpenAI Universe
Conclusion
Chapter 4: Applying Python to Reinforcement Learning
Q Learning with Python
The Maze Environment Python File
The RL_Brain Python File
Updating the Function
Using the MDP Toolbox in Python
Understanding Swarm Intelligence
Applications of Swarm Intelligence
Ant-Based Routing
Crowd Simulations
Human Swarming
Swarm Grammars
Swarmic Art
The Rastrigin Function
Swarm Intelligence in Python
Building a Game AI
The Entire TFLearn Code
Conclusion
Chapter 5: Reinforcement Learning with Keras, TensorFlow, and ChainerRL
What Is Keras?
Using Keras for Reinforcement Learning
Using ChainerRL
Installing ChainerRL
Pipeline for Using ChainerRL
Deep Q Learning: Using Keras and TensorFlow
Installing Keras-rl
Training with Keras-rl
Conclusion
Chapter 6: Google’s DeepMind and the Future of Reinforcement Learning
Google DeepMind
Google AlphaGo
What Is AlphaGo?
Monte Carlo Search
Man vs. Machines
Positive Aspects of AI
Negative Aspects of AI
Conclusion
Index
