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


To experiment with the methods in this chapter, we'll use roboschool, which uses PyBullet as a physics engine and has 13 environments of various complexity. PyBullet has similar environments, but at the time of writing it wasn't possible to create several instances of the same environment due to internal OpenGL issue. In this chapter, we'll get in touch with two problems: RoboschoolHalfCheetah-v1, which models a two-legged creature and RoboschoolAnt-v1, which has four legs. The state and action spaces of them are very similar to the Minitaur environment that we saw in the previous chapter: the state includes characteristics from joints and actions are activations of those joints. The goal for both is to move as far as possible, minimizing the energy spent.

Figure 1: Screenshots of two roboschool environments: RoboschoolHalfCheetah and RoboschoolAnt

To install roboschool, you need to follow the instructions on This requires extra components to...