Book Image

Keras Reinforcement Learning Projects

By : Giuseppe Ciaburro
Book Image

Keras Reinforcement Learning Projects

By: Giuseppe Ciaburro

Overview of this book

Reinforcement learning has evolved a lot in the last couple of years and proven to be a successful technique in building smart and intelligent AI networks. Keras Reinforcement Learning Projects installs human-level performance into your applications using algorithms and techniques of reinforcement learning, coupled with Keras, a faster experimental library. The book begins with getting you up and running with the concepts of reinforcement learning using Keras. You’ll learn how to simulate a random walk using Markov chains and select the best portfolio using dynamic programming (DP) and Python. You’ll also explore projects such as forecasting stock prices using Monte Carlo methods, delivering vehicle routing application using Temporal Distance (TD) learning algorithms, and balancing a Rotating Mechanical System using Markov decision processes. Once you’ve understood the basics, you’ll move on to Modeling of a Segway, running a robot control system using deep reinforcement learning, and building a handwritten digit recognition model in Python using an image dataset. Finally, you’ll excel in playing the board game Go with the help of Q-Learning and reinforcement learning algorithms. By the end of this book, you’ll not only have developed hands-on training on concepts, algorithms, and techniques of reinforcement learning but also be all set to explore the world of AI.

Related Content you might be interested in

Current Title:

Small book image
Keras Reinforcement Learning Projects
Giuseppe Ciaburro
Sep, 2018 | 288 pages
Small book image
Hands-On Machine Learning on Google Cloud Platform
Alexis Perrier | V Kishore Ayyadevara | Giuseppe Ciaburro
Apr, 2018 | 500 pages
Small book image
Python Machine Learning Cookbook,
Prateek Joshi | Giuseppe Ciaburro
Mar, 2019 | 642 pages
Small book image
Hands-On Simulation Modeling with Python
Giuseppe Ciaburro
Jul, 2020 | 346 pages
Table of Contents (13 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Overview of Keras Reinforcement Learning
Overview of Keras Reinforcement Learning
Basic concepts of machine learning
Getting started with reinforcement learning
Reinforcement learning algorithms
Summary
2
Simulating Random Walks
Simulating Random Walks
Random walks
Markov chains
Summary
3
Optimal Portfolio Selection
Optimal Portfolio Selection
Dynamic Programming
Optimizing a financial portfolio
Solving the knapsack problem using Dynamic Programming
Summary
4
Forecasting Stock Market Prices
Forecasting Stock Market Prices
Monte Carlo methods
Amazon stock price prediction using Python
Summary
5
Delivery Vehicle Routing Application
Delivery Vehicle Routing Application
Temporal difference learning
Basics of graph theory
Finding the shortest path
The Vehicle Routing Problem
Summary
6
Continuous Balancing of a Rotating Mechanical System
Continuous Balancing of a Rotating Mechanical System
Neural network basic concepts
Classifying breast cancer using the neural network
Deep reinforcement learning
Continuous control with deep reinforcement learning
Summary
7
Dynamic Modeling of a Segway as an Inverted Pendulum System
Dynamic Modeling of a Segway as an Inverted Pendulum System
How Segways work
OpenAI Gym
The CartPole system
Summary
8
Robot Control System Using Deep Reinforcement Learning
Robot Control System Using Deep Reinforcement Learning
Robot control
The FrozenLake environment
Summary
9
Handwritten Digit Recognizer
Handwritten Digit Recognizer
Handwritten digit recognition
Handwritten digit recognition using an autoencoder
Deep autoencoder Q-learning
Summary
10
Playing the Board Game Go
Playing the Board Game Go
Game theory
The Go game
The AlphaGo project
Summary
11
What's Next?
What's Next?
Reinforcement-learning applications in real life
Next steps for reinforcement learning
Summary
12
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Temporal difference learning

TD learning algorithms are based on reducing the differences between estimates made by the agent at different times. Q-learning, which we will discuss in the following section, is a TD algorithm, but it is based on the difference between states in immediately adjacent instants. TD is more generic and may consider moments and states further away.

TD is a combination of the ideas of the MC method and DP, both of which can be summarized as follows:

  • MC methods allow the solving of reinforcement learning problems based on the average of the obtained results
  • DP represents a set of algorithms that can be used to calculate an optimal policy given a perfect model of the environment in the form of a Markov Decision Process (MDP)

The following can be said of TD methods:

  • They inherit from MC methods the idea of learning directly from experience accumulated...
Previous Section
End of Section 2
Next Section