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

Evolution strategies

The subset of black-box optimization methods is called evolution strategies (ES) and has been inspired by the evolution process, where the most successful individuals have the highest influence on the overall direction of the search. There are many different methods that fall into this class and in this chapter, we'll consider the approach taken by OpenAI researchers Tim Salimans, Jonathan Ho, and others in their paper, Evolution Strategies as a Scalable Alternative to Reinforcement Learning [1], published in March 2017.

The underlying idea of ES methods is simple: on every iteration, we perform random perturbation of our current policy parameters and evaluate the resulting policy fitness function. Then we adjust the policy weights proportional to the relative fitness function value.

The concrete method used in the paper above is called Covariance Matrix Adaptation Evolution Strategy (CMA-ES) in which the perturbation performed is the random noise sampled from the zero...