Hands-on Reinforcement Learning with TensorFlow [Video]

More Information
  • Get to know important features of RL that are used for AI
  • Create agents to perform complex tasks using RL
  • Implement the Q-learning and Q-network algorithms for RL
  • Apply Deepmind’s Deep Q-network architecture to improve performance
  • See improvisations of DQN (Double DQN and Dueling DQN) and other state of the art RL techniques
  • Test your RL agent on myriad of games and other environments using the Open AI gym

You’ve probably heard of Deepmind’s AI playing games and getting really good at playing them (like AlphaGo beating the Go world champion). Such agents are built with the help of a paradigm of machine learning called “Reinforcement Learning” (RL).

In this course, you’ll walk through different approaches to RL. You’ll move from a simple Q-learning to a more complex, deep RL architecture and implement your algorithms using Tensorflow’s Python API. You’ll be training your agents on two different games in a number of complex scenarios to make them more intelligent and perceptive.
By the end of this course, you’ll be able to implement RL-based solutions in your projects from scratch using Tensorflow and Python.

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

Style and Approach

A practical guide that demonstrates how to create smart agents by implementing different Reinforcement Learning techniques with Python and Tensorflow, and how to easily improve their performance in different games and environments.

  • Practical training in the Reinforcement Learning architecture for training agents
  • Work with important open source Reinforcement Learning frameworks to get an in-depth knowledge of its functions
  • A Production-ready approach to training Reinforcement Learning agents in Tensorflow to take on real-world projects
Course Length 3 hours 42 minutes
ISBN 9781788995368
Date Of Publication 30 Aug 2018


Satwik Kansal

Satwik Kansal is a Software Developer with more than 2 years experience in the domain of Data Science. He’s a big open source and Python aficionado, currently the top-rated Python developer in India, and an active Python blogger. Satwik likes writing in-depth articles on various technical topics related to Data Science, Decentralized Applications, and Python. Apart from working full time as a software engineer, you may find him guest blogging for IBM DeveloperWorks and Learndatasci, freelancing, participating in Hackathons, or attending tech-conferences.