Reinforcement Learning with TensorFlow & TRFL [Video]

More Information
Learn
  • Build projects with TRFL and TensorFlow and integrate essential RL building blocks into existing code
  • Save time spent implementing, testing, and debugging by increasing code reliability
  • Relate TRFL methods to the leading RL algorithms and theory
  • Discover improvements to RL algorithms such as DQN and DDPG with TRFL blocks—for example, advanced target network updating, Double Q Learning, and Distributional Q Learning
  • Use cutting-edge techniques behind IMPALA and UNREAL such as V-Trace and Pixel Control
  • Modify RL agents to include multistep reward techniques such as TD lambda
  • Explore policy gradient techniques used in leading algorithms with TRFL methods for discrete and continuous action spaces
  • Create TRFL-based RL agents with classic RL methods such as TD Learning, Q Learning, and SARSA
About

The TRFL library is a collection of key algorithmic components that are used for a large number of DeepMind agents such as DQN, DDPG, and the Importance of Weighted Actor Learner Architecture. With this course, you will learn to implement classical RL algorithms as well as other cutting-edge techniques.

This course will help you get up-to-speed with the TRFL library quickly, so you can start building your own RL agents. Without wasting much time on theory, the course dives straightaway into designing and implementing RL algorithms.

By the end, you will be quite familiar with the tool and will be ready to put your knowledge into practice in your own projects.

The code bundle for this course is available at - https://github.com/PacktPublishing/Hands-On-Reinforcement-Learning-with-TensorFlow-TRFL

Style and Approach

In each section of the course, we walk through part of the TRFL library. We explain how TRFL is used with clear code examples that highlight integrating TRFL into TensorFlow code, making it easy to deploy TRFL in new or existing projects. While this course emphasizes practical TRFL usage, we provide explanations that relate the TRFL library to the underlying theory and provide further resources for those wanting to know more.

Features
  • Hands-on emphasis on code examples to get you experienced with TRFL quickly.
  • Straightforward implementations of TRFL that let you utilize a trusted codebase in your projects. Save time implementing RL agents and algorithms, unit testing, and debugging code.
  • Covers the TRFL library more comprehensively than any other course. Examples teach the easy integration and expansion of RL algorithms with TRFL building blocks.
Course Length 1 hour 19 minutes
ISBN 9781789950748
Date Of Publication 18 Apr 2019

Authors

Jim DiLorenzo

Colibri Digital is a technology consultancy company founded in 2015 by James Cross and Ingrid Funie. The company works to help its clients navigate the rapidly changing and complex world of emerging technologies, with deep expertise in areas such as big data, data science, machine learning, and Cloud computing.

Over the past few years, they have worked with some of the World's largest and most prestigious companies, including a tier 1 investment bank, a leading management consultancy group, and one of the World's most popular soft drinks companies, helping each of them to better make sense of its data, and process it in more intelligent ways.

The company lives by its motto: Data -> Intelligence -> Action.

Jim DiLorenzo is a freelance programmer and Reinforcement Learning enthusiast. He graduated from Columbia University and is working on his Masters in Computer Science. He has used TRFL in his own RL experiments and when implementing scientific papers into code.