Book Image

The Reinforcement Learning Workshop

By : Alessandro Palmas, Emanuele Ghelfi, Dr. Alexandra Galina Petre, Mayur Kulkarni, Anand N.S., Quan Nguyen, Aritra Sen, Anthony So, Saikat Basak
Book Image

The Reinforcement Learning Workshop

By: Alessandro Palmas, Emanuele Ghelfi, Dr. Alexandra Galina Petre, Mayur Kulkarni, Anand N.S., Quan Nguyen, Aritra Sen, Anthony So, Saikat Basak

Overview of this book

Various intelligent applications such as video games, inventory management software, warehouse robots, and translation tools use reinforcement learning (RL) to make decisions and perform actions that maximize the probability of the desired outcome. This book will help you to get to grips with the techniques and the algorithms for implementing RL in your machine learning models. Starting with an introduction to RL, youÔÇÖll be guided through different RL environments and frameworks. YouÔÇÖll learn how to implement your own custom environments and use OpenAI baselines to run RL algorithms. Once youÔÇÖve explored classic RL techniques such as Dynamic Programming, Monte Carlo, and TD Learning, youÔÇÖll understand when to apply the different deep learning methods in RL and advance to deep Q-learning. The book will even help you understand the different stages of machine-based problem-solving by using DARQN on a popular video game Breakout. Finally, youÔÇÖll find out when to use a policy-based method to tackle an RL problem. By the end of The Reinforcement Learning Workshop, youÔÇÖll be equipped with the knowledge and skills needed to solve challenging problems using reinforcement learning.
Table of Contents (14 chapters)
Preface
Free Chapter
2
2. Markov Decision Processes and Bellman Equations

Summary

In this chapter, you have explored gradient-based and gradient-free methods of algorithm optimization, with an emphasis on the potential of evolutionary algorithms – in particular, GAs – to solve optimization problems, such as sub-optimal solutions, using a nature-inspired approach. GAs consist of specific elements, such as population generation, parent selection, parent reproduction or crossover, and finally mutation occurrence, which they use to create a binary optimal solution.

Then, the use of GAs for hyperparameter tuning and selection for neural networks was explored, helping us to find the most suitable window size and unit number. We saw implementations of state-of-the-art algorithms that combined deep neural networks and evolutionary strategies, such as NEAT for XNOR output estimation. Finally, you had a chance to implement what was studied in this chapter through an OpenAI Gym cart-pole simulation, where we examined the application of GAs for parameter...