Reinforcement Learning: With Open Ai, Tensorflow and Keras Using Python

ISBN-13: 9781484232842 / Angielski / Miękka / 2017 / 167 str.

Abhishek Nandy; Manisha Biswas

Spis treści

Chapter 1:  Reinforcement Learning basics

Chapter Goal: This chapter covers the basics needed for AI,ML and Deep Learning.Relation between them and differences.

No of pages 30

Sub -Topics

1. Reinforcement Learning

2. The flow

3. Faces of Reinforcement Learning

4. 5. Environments6. The depiction of inter relation between Agents and EnvironmentDeep Learning
Chapter 2:  Theory and AlgorithmsChapter Goal :This Chapter covers the theory  of Reinforcement Learning and Algorithms.

No of pages : 60

Sub-topics

1 . Problem scenarios in Reinforcement Learningins

2. Markov Decision process

3. SARSA

4.Q learning

5.Value Functions

6.Dynamic Programming and Policies

7.Approaches to RL

Chapter 3: Open AI basics

Chapter Goal: In this chapter we will cover the basics of

Open AI gym and universe and

then move forward for installing it.

No of pages: 40

Sub - Topics:

1. What are Open AI environments

2. Installation of Open AI Gym and Universe in Ubuntu

3. Difference between Open AI Gym and Universe

Chapter 4: Getting to know Open AI  and Open AI gym the developers way

Chapter Goal: We will use Python to start the programming and cover topics accordingly

No of pages: 60

Sub - Topics: 

1. Open AI,Open AI Gym and python

2. Setting up the environment

3. Examples

4 Swarm Intelligence using python

5.Markov Decision process toolbox for Python

6.Implementing a Game AI with Reinforcement Learning

Chapter 5: Reinforcement learning using Tensor Flow environment and Keras

Chapter Goal: We cover Reinforcement Learning in terms of Tensorflow and Keras

N

o of pages: 40

Sub - Topics:  

1. Tensorflow and Reinforcement Learning

2. Q learning with Tensor Flow

3. Keras

4. Keras and Reinforcement Learning

Chapter 6  Google’s DeepMind and the future of Reinforcement Learning

Chapter Goal: We cover the descriptions of the above the content.

No of pages: 25

Sub - Topics:  

1. Google’s Deep Mind

2. Future of Reinforcement Learning 

3. Man VS Machines where is it Heading to.

O autorze

Abhishek Nandy is B.Tech in IT and he is a constant learner.He is Microsoft MVP at Windows Platform,Intel Black belt Developer as well as Intel Software Innovator he has keen interest on AI,IoT and Game Development. Currently serving as a Application Architect in an IT Firm as well as consulting AI,IoT as well doing projects on AI,ML and Deep learning.He also is an AI trainer and driving the technical part of Intel AI Student developer program.He was involved in the first Make in India initiative where he was among top 50 innovators and got trained in IIMA.

Manisha Biswas is BTech in Information Technology and currently working as a Software Developer at Insync Tech-Fin Solutions Ltd,in kolkata, India. I'm involved with several areas of technology including Web Development, IoT,Soft Computing and Artificial Intelligence. I am an Intel Software Innovator and I was also awarded the SHRI DEWANG MEHTA IT AWARDS 2016 by NASSCOM,a certificate of excellence for top academic scores. I have very recently formed a WOMEN IN TECHNOLOGY Community at KoIKata,India to empower women to learn and explore new technologies.I always like to invent things,create something new,or to invent a new look for the old things. When not in front of my terminal, I am an explorer, a foodie, a doodler and a dreamer. I am always very passionate to share my knowledge and ideas with others. I am following the passion and doing the same currently by sharing my experiences to the community so that others can learn and also give shape to my ideas in a new way this lead me to become Google Women Techmakers Kolkata Chapter Lead.

Blurb

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. 

You will:

• 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