Foundations of Deep Reinforcement Learning : Theory and Practice in Python

Graesser, Laura; Keng, Wah Loon

ISBN 10: 0135172381 / ISBN 13: 9780135172384

Published by Addison-Wesley Professional, 2019

About this Item

Seller Inventory # 35106043-n

Bibliographic Details

Title: Foundations of Deep Reinforcement Learning :...

Publisher: Addison-Wesley Professional

Publication Date: 2019

Binding: Soft cover

Condition: New

About this title

Synopsis:

In just a few years, deep reinforcement learning (DRL) systems such as DeepMinds DQN have yielded remarkable results. This hybrid approach to machine learning shares many similarities with human learning: its unsupervised self-learning, self-discovery of strategies, usage of memory, balance of exploration and exploitation, and its exceptional flexibility. Exciting in its own right, DRL may presage even more remarkable advances in general artificial intelligence. 
Deep Reinforcement Learning in Python: A Hands-On Introduction is the fastest and most accessible way to get started with DRL. The authors teach through practical hands-on examples presented with their advanced OpenAI Lab framework. While providing a solid theoretical overview, they emphasize building intuition for the theory, rather than a deep mathematical treatment of results. Coverage includes: 

• Components of an RL system, including environment and agents
• Value-based algorithms: SARSA, Q-learning and extensions, offline learning
• Policy-based algorithms: REINFORCE and extensions; comparisons with value-based techniques
• Combined methods: Actor-Critic and extensions; scalability through async methods
• Agent evaluation
• Advanced and experimental techniques, and more

About the Author:

Laura Graesser enjoys experimenting with, and writing about, machine learning techniques. Currently she is studying for an MS in Computer Science. She is particularly interested in deep learning algorithms and their application to reinforcement learning, computer vision, and NLP. Most recently, she is interested in combining reinforcement learning with supervised learning, knowledge distillation, and in tackling multi-modal and multi-task learning.
Wah Loon Keng likes building softwares for the research and application of theories in Computer Science and AI. He is an active open source contributor, and the creator of the data science platform at Eligible Inc. As a student, he did research on quantum foundation, computer science and mathematics. He is always interested in the theories of intelligence, especially reinforcement learning, semantics, and intuitive theories of mind. With his engineering skills, he is building experiment frameworks to test these theories, and OpenAI Lab is one.