Deep Reinforcement Learning: Theory and Practice in Python

Deep Reinforcement Learning: Theory and Practice by Laura Graesser and Wah Loon Keng

Interested in combining the power of deep learning and reinforcement learning? This book provides a deep and practical approach to this exciting field of machine learning. You will learn how virtual agents learn to solve sequential tasks and make optimal decisions.

Breakthrough Achievements in Training Virtual Agents

Recent decades have been marked by extraordinary achievements in training agents that interact with various environments. From single-player and multi-player games to Atari video games and Dota, and even in robotics – reinforcement learning demonstrates its immense potential.

A Unique Approach: Theory and Practice of Deep Reinforcement Learning

This book is a unique blend of theory and practice. Laura Graesser and Wah Loon Keng start with foundational knowledge, gradually and thoroughly explaining the theory and algorithms of deep reinforcement learning. Special attention is given to practical implementation – all concepts are demonstrated using examples and the SLM Lab software library.

Practical Application and the SLM Lab Library

The authors, Laura Graesser and Wah Loon Keng, not only cover the theory but also show how to apply deep reinforcement learning in practice. You will master the use of the SLM Lab library, enabling you to independently develop and train intelligent agents.

Who is this book for?

This guide is ideal for computer science students and software developers familiar with the basic principles of machine learning and proficient in Python. The book will be an excellent resource for those who want to master deep reinforcement learning and apply it in their projects.