Cover
Copyright
Contents
About the Authors
Introduction
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
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
3: OpenAI Basics
Getting to Know OpenAI
Installing OpenAI Gym and OpenAI Universe
Working with OpenAI Gym and OpenAI
More Simulations
OpenAI Universe
Conclusion
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
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
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