You're reading from TensorFlow 2 Reinforcement Learning Cookbook Over 50 recipes to help you build, train, and deploy learning agents for real-world applications

Product type Paperback

Published in Jan 2021

Publisher Packt

ISBN-13 9781838982546

Length 472 pages

Edition 1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Reinforcement Learning

Author (1):

Palanisamy

View More author details

Table of Contents (11) Chapters

Preface

1. Chapter 1: Developing Building Blocks for Deep Reinforcement Learning Using Tensorflow 2.x

2. Chapter 2: Implementing Value-Based, Policy-Based, and Actor-Critic Deep RL Algorithms FREE CHAPTER

3. Chapter 3: Implementing Advanced RL Algorithms

4. Chapter 4: Reinforcement Learning in the Real World – Building Cryptocurrency Trading Agents

5. Chapter 5: Reinforcement Learning in the Real World – Building Stock/Share Trading Agents

6. Chapter 6: Reinforcement Learning in the Real World – Building Intelligent Agents to Complete Your To-Dos

7. Chapter 7: Deploying Deep RL Agents to the Cloud

8. Chapter 8: Distributed Training for Accelerated Development of Deep RL Agents

9. Chapter 9: Deploying Deep RL Agents on Multiple Platforms

10. Other Books You May Enjoy

Leave a review - let other readers know what you think

Packaging Deep RL agents for mobile and IoT devices using TensorFlow Lite

This recipe will show how you can leverage the open source TensorFlow Lite (TFLite) framework for serving your Deep RL agents on mobile, IoT, and embedded devices. We will implement a complete script to build, train, and export an agent model that you can load into a mobile or embedded device. We will explore two methods to generate the TFLite model for our agent. The first method involves saving and exporting the agent models in TensorFlow's SavedModel file format and then using a command-line converter. The second method leverages the Python API to directly generate the TFLite models.

Let's get started!

Getting ready

To complete this recipe, you will first need to activate the tf2rl-cookbook Python/conda virtual environment. Make sure to update the environment to match the latest conda environment specification file (tfrl-cookbook.yml) in the cookbook's code repo. If the following imports...