Book Image

Deep Reinforcement Learning Hands-On

By : Maxim Lapan
Book Image

Deep Reinforcement Learning Hands-On

By: Maxim Lapan

Overview of this book

Deep Reinforcement Learning Hands-On is a comprehensive guide to the very latest DL tools and their limitations. You will evaluate methods including Cross-entropy and policy gradients, before applying them to real-world environments. Take on both the Atari set of virtual games and family favorites such as Connect4. The book provides an introduction to the basics of RL, giving you the know-how to code intelligent learning agents to take on a formidable array of practical tasks. Discover how to implement Q-learning on 'grid world' environments, teach your agent to buy and trade stocks, and find out how natural language models are driving the boom in chatbots.
Table of Contents (23 chapters)
Deep Reinforcement Learning Hands-On
Other Books You May Enjoy

N-step DQN

The first improvement that we'll implement and evaluate is quite an old one. It was first introduced in the paper by Richard Sutton ([2] Sutton, 1988). To get the idea, let's look at the Bellman update used in Q-learning once again.

This equation is recursive, which means that we can express in terms of itself, which gives us this result:

Value ra,t+1 means local reward at time t+1, after issuing action a. However, if we assume that our action a at the step t+1 was chosen optimally, or close to optimally, we can omit maxa and operation and obtain this:

This value could be unrolled again and again any number of times. As you may guess, this unrolling can be easily applied to our DQN update by replacing one-step transition sampling with longer transition sequences of n-steps. To understand why this unrolling will help us to speed up training, let's consider the example illustrated below. Here we have a simple environment of four states, s1, s2, s3, s4, and the only action available...