Robot Learning

Robot Learning

Author: J. H. Connell

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 247

ISBN-13: 1461531845

DOWNLOAD EBOOK

Building a robot that learns to perform a task has been acknowledged as one of the major challenges facing artificial intelligence. Self-improving robots would relieve humans from much of the drudgery of programming and would potentially allow operation in environments that were changeable or only partially known. Progress towards this goal would also make fundamental contributions to artificial intelligence by furthering our understanding of how to successfully integrate disparate abilities such as perception, planning, learning and action. Although its roots can be traced back to the late fifties, the area of robot learning has lately seen a resurgence of interest. The flurry of interest in robot learning has partly been fueled by exciting new work in the areas of reinforcement earning, behavior-based architectures, genetic algorithms, neural networks and the study of artificial life. Robot Learning gives an overview of some of the current research projects in robot learning being carried out at leading universities and research laboratories in the United States. The main research directions in robot learning covered in this book include: reinforcement learning, behavior-based architectures, neural networks, map learning, action models, navigation and guided exploration.


Book Synopsis Robot Learning by : J. H. Connell

Download or read book Robot Learning written by J. H. Connell and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 247 pages. Available in PDF, EPUB and Kindle. Book excerpt: Building a robot that learns to perform a task has been acknowledged as one of the major challenges facing artificial intelligence. Self-improving robots would relieve humans from much of the drudgery of programming and would potentially allow operation in environments that were changeable or only partially known. Progress towards this goal would also make fundamental contributions to artificial intelligence by furthering our understanding of how to successfully integrate disparate abilities such as perception, planning, learning and action. Although its roots can be traced back to the late fifties, the area of robot learning has lately seen a resurgence of interest. The flurry of interest in robot learning has partly been fueled by exciting new work in the areas of reinforcement earning, behavior-based architectures, genetic algorithms, neural networks and the study of artificial life. Robot Learning gives an overview of some of the current research projects in robot learning being carried out at leading universities and research laboratories in the United States. The main research directions in robot learning covered in this book include: reinforcement learning, behavior-based architectures, neural networks, map learning, action models, navigation and guided exploration.

Recent Advances in Robot Learning

Recent Advances in Robot Learning

Author: Judy A. Franklin

Publisher: Springer Science & Business Media

Published: 2012-12-06

Total Pages: 218

ISBN-13: 1461304717

DOWNLOAD EBOOK

Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. Since robot learning involves decision making, there is an inherent active learning issue. Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. On the other hand, machine learning is also highly attractive to robotics. There is a great variety of open problems in robotics that defy a static, hand-coded solution. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3).


Book Synopsis Recent Advances in Robot Learning by : Judy A. Franklin

Download or read book Recent Advances in Robot Learning written by Judy A. Franklin and published by Springer Science & Business Media. This book was released on 2012-12-06 with total page 218 pages. Available in PDF, EPUB and Kindle. Book excerpt: Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. Since robot learning involves decision making, there is an inherent active learning issue. Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. On the other hand, machine learning is also highly attractive to robotics. There is a great variety of open problems in robotics that defy a static, hand-coded solution. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3).

Deep Learning for Robot Perception and Cognition

Deep Learning for Robot Perception and Cognition

Author: Alexandros Iosifidis

Publisher: Academic Press

Published: 2022-02-04

Total Pages: 638

ISBN-13: 0323885721

DOWNLOAD EBOOK

Deep Learning for Robot Perception and Cognition introduces a broad range of topics and methods in deep learning for robot perception and cognition together with end-to-end methodologies. The book provides the conceptual and mathematical background needed for approaching a large number of robot perception and cognition tasks from an end-to-end learning point-of-view. The book is suitable for students, university and industry researchers and practitioners in Robotic Vision, Intelligent Control, Mechatronics, Deep Learning, Robotic Perception and Cognition tasks. Presents deep learning principles and methodologies Explains the principles of applying end-to-end learning in robotics applications Presents how to design and train deep learning models Shows how to apply deep learning in robot vision tasks such as object recognition, image classification, video analysis, and more Uses robotic simulation environments for training deep learning models Applies deep learning methods for different tasks ranging from planning and navigation to biosignal analysis


Book Synopsis Deep Learning for Robot Perception and Cognition by : Alexandros Iosifidis

Download or read book Deep Learning for Robot Perception and Cognition written by Alexandros Iosifidis and published by Academic Press. This book was released on 2022-02-04 with total page 638 pages. Available in PDF, EPUB and Kindle. Book excerpt: Deep Learning for Robot Perception and Cognition introduces a broad range of topics and methods in deep learning for robot perception and cognition together with end-to-end methodologies. The book provides the conceptual and mathematical background needed for approaching a large number of robot perception and cognition tasks from an end-to-end learning point-of-view. The book is suitable for students, university and industry researchers and practitioners in Robotic Vision, Intelligent Control, Mechatronics, Deep Learning, Robotic Perception and Cognition tasks. Presents deep learning principles and methodologies Explains the principles of applying end-to-end learning in robotics applications Presents how to design and train deep learning models Shows how to apply deep learning in robot vision tasks such as object recognition, image classification, video analysis, and more Uses robotic simulation environments for training deep learning models Applies deep learning methods for different tasks ranging from planning and navigation to biosignal analysis

Learn Robotics with Raspberry Pi

Learn Robotics with Raspberry Pi

Author: Matt Timmons-Brown

Publisher: No Starch Press

Published: 2019-01-22

Total Pages: 240

ISBN-13: 1593279213

DOWNLOAD EBOOK

In Learn Robotics with Raspberry Pi, you'll learn how to build and code your own robot projects with just the Raspberry Pi microcomputer and a few easy-to-get components - no prior experience necessary! Learn Robotics with Raspberry Pi will take you from inexperienced maker to robot builder. You'll start off building a two-wheeled robot powered by a Raspberry Pi minicomputer and then program it using Python, the world's most popular programming language. Gradually, you'll improve your robot by adding increasingly advanced functionality until it can follow lines, avoid obstacles, and even recognize objects of a certain size and color using computer vision. Learn how to: - Control your robot remotely using only a Wii remote - Teach your robot to use sensors to avoid obstacles - Program your robot to follow a line autonomously - Customize your robot with LEDs and speakers to make it light up and play sounds - See what your robot sees with a Pi Camera As you work through the book, you'll learn fundamental electronics skills like how to wire up parts, use resistors and regulators, and determine how much power your robot needs. By the end, you'll have learned the basics of coding in Python and know enough about working with hardware like LEDs, motors, and sensors to expand your creations beyond simple robots.


Book Synopsis Learn Robotics with Raspberry Pi by : Matt Timmons-Brown

Download or read book Learn Robotics with Raspberry Pi written by Matt Timmons-Brown and published by No Starch Press. This book was released on 2019-01-22 with total page 240 pages. Available in PDF, EPUB and Kindle. Book excerpt: In Learn Robotics with Raspberry Pi, you'll learn how to build and code your own robot projects with just the Raspberry Pi microcomputer and a few easy-to-get components - no prior experience necessary! Learn Robotics with Raspberry Pi will take you from inexperienced maker to robot builder. You'll start off building a two-wheeled robot powered by a Raspberry Pi minicomputer and then program it using Python, the world's most popular programming language. Gradually, you'll improve your robot by adding increasingly advanced functionality until it can follow lines, avoid obstacles, and even recognize objects of a certain size and color using computer vision. Learn how to: - Control your robot remotely using only a Wii remote - Teach your robot to use sensors to avoid obstacles - Program your robot to follow a line autonomously - Customize your robot with LEDs and speakers to make it light up and play sounds - See what your robot sees with a Pi Camera As you work through the book, you'll learn fundamental electronics skills like how to wire up parts, use resistors and regulators, and determine how much power your robot needs. By the end, you'll have learned the basics of coding in Python and know enough about working with hardware like LEDs, motors, and sensors to expand your creations beyond simple robots.

Robot-Proof

Robot-Proof

Author: Joseph E. Aoun

Publisher: MIT Press

Published: 2018-08-14

Total Pages: 211

ISBN-13: 0262535971

DOWNLOAD EBOOK

How to educate the next generation of college students to invent, to create, and to discover—filling needs that even the most sophisticated robot cannot. Driverless cars are hitting the road, powered by artificial intelligence. Robots can climb stairs, open doors, win Jeopardy, analyze stocks, work in factories, find parking spaces, advise oncologists. In the past, automation was considered a threat to low-skilled labor. Now, many high-skilled functions, including interpreting medical images, doing legal research, and analyzing data, are within the skill sets of machines. How can higher education prepare students for their professional lives when professions themselves are disappearing? In Robot-Proof, Northeastern University president Joseph Aoun proposes a way to educate the next generation of college students to invent, to create, and to discover—to fill needs in society that even the most sophisticated artificial intelligence agent cannot. A “robot-proof” education, Aoun argues, is not concerned solely with topping up students' minds with high-octane facts. Rather, it calibrates them with a creative mindset and the mental elasticity to invent, discover, or create something valuable to society—a scientific proof, a hip-hop recording, a web comic, a cure for cancer. Aoun lays out the framework for a new discipline, humanics, which builds on our innate strengths and prepares students to compete in a labor market in which smart machines work alongside human professionals. The new literacies of Aoun's humanics are data literacy, technological literacy, and human literacy. Students will need data literacy to manage the flow of big data, and technological literacy to know how their machines work, but human literacy—the humanities, communication, and design—to function as a human being. Life-long learning opportunities will support their ability to adapt to change. The only certainty about the future is change. Higher education based on the new literacies of humanics can equip students for living and working through change.


Book Synopsis Robot-Proof by : Joseph E. Aoun

Download or read book Robot-Proof written by Joseph E. Aoun and published by MIT Press. This book was released on 2018-08-14 with total page 211 pages. Available in PDF, EPUB and Kindle. Book excerpt: How to educate the next generation of college students to invent, to create, and to discover—filling needs that even the most sophisticated robot cannot. Driverless cars are hitting the road, powered by artificial intelligence. Robots can climb stairs, open doors, win Jeopardy, analyze stocks, work in factories, find parking spaces, advise oncologists. In the past, automation was considered a threat to low-skilled labor. Now, many high-skilled functions, including interpreting medical images, doing legal research, and analyzing data, are within the skill sets of machines. How can higher education prepare students for their professional lives when professions themselves are disappearing? In Robot-Proof, Northeastern University president Joseph Aoun proposes a way to educate the next generation of college students to invent, to create, and to discover—to fill needs in society that even the most sophisticated artificial intelligence agent cannot. A “robot-proof” education, Aoun argues, is not concerned solely with topping up students' minds with high-octane facts. Rather, it calibrates them with a creative mindset and the mental elasticity to invent, discover, or create something valuable to society—a scientific proof, a hip-hop recording, a web comic, a cure for cancer. Aoun lays out the framework for a new discipline, humanics, which builds on our innate strengths and prepares students to compete in a labor market in which smart machines work alongside human professionals. The new literacies of Aoun's humanics are data literacy, technological literacy, and human literacy. Students will need data literacy to manage the flow of big data, and technological literacy to know how their machines work, but human literacy—the humanities, communication, and design—to function as a human being. Life-long learning opportunities will support their ability to adapt to change. The only certainty about the future is change. Higher education based on the new literacies of humanics can equip students for living and working through change.

Learning for Adaptive and Reactive Robot Control

Learning for Adaptive and Reactive Robot Control

Author: Aude Billard

Publisher: MIT Press

Published: 2022-02-08

Total Pages: 425

ISBN-13: 0262367017

DOWNLOAD EBOOK

Methods by which robots can learn control laws that enable real-time reactivity using dynamical systems; with applications and exercises. This book presents a wealth of machine learning techniques to make the control of robots more flexible and safe when interacting with humans. It introduces a set of control laws that enable reactivity using dynamical systems, a widely used method for solving motion-planning problems in robotics. These control approaches can replan in milliseconds to adapt to new environmental constraints and offer safe and compliant control of forces in contact. The techniques offer theoretical advantages, including convergence to a goal, non-penetration of obstacles, and passivity. The coverage of learning begins with low-level control parameters and progresses to higher-level competencies composed of combinations of skills. Learning for Adaptive and Reactive Robot Control is designed for graduate-level courses in robotics, with chapters that proceed from fundamentals to more advanced content. Techniques covered include learning from demonstration, optimization, and reinforcement learning, and using dynamical systems in learning control laws, trajectory planning, and methods for compliant and force control . Features for teaching in each chapter: applications, which range from arm manipulators to whole-body control of humanoid robots; pencil-and-paper and programming exercises; lecture videos, slides, and MATLAB code examples available on the author’s website . an eTextbook platform website offering protected material[EPS2] for instructors including solutions.


Book Synopsis Learning for Adaptive and Reactive Robot Control by : Aude Billard

Download or read book Learning for Adaptive and Reactive Robot Control written by Aude Billard and published by MIT Press. This book was released on 2022-02-08 with total page 425 pages. Available in PDF, EPUB and Kindle. Book excerpt: Methods by which robots can learn control laws that enable real-time reactivity using dynamical systems; with applications and exercises. This book presents a wealth of machine learning techniques to make the control of robots more flexible and safe when interacting with humans. It introduces a set of control laws that enable reactivity using dynamical systems, a widely used method for solving motion-planning problems in robotics. These control approaches can replan in milliseconds to adapt to new environmental constraints and offer safe and compliant control of forces in contact. The techniques offer theoretical advantages, including convergence to a goal, non-penetration of obstacles, and passivity. The coverage of learning begins with low-level control parameters and progresses to higher-level competencies composed of combinations of skills. Learning for Adaptive and Reactive Robot Control is designed for graduate-level courses in robotics, with chapters that proceed from fundamentals to more advanced content. Techniques covered include learning from demonstration, optimization, and reinforcement learning, and using dynamical systems in learning control laws, trajectory planning, and methods for compliant and force control . Features for teaching in each chapter: applications, which range from arm manipulators to whole-body control of humanoid robots; pencil-and-paper and programming exercises; lecture videos, slides, and MATLAB code examples available on the author’s website . an eTextbook platform website offering protected material[EPS2] for instructors including solutions.

Robot Learning from Human Demonstration

Robot Learning from Human Demonstration

Author: Sonia Dechter

Publisher: Springer Nature

Published: 2022-06-01

Total Pages: 109

ISBN-13: 3031015703

DOWNLOAD EBOOK

Learning from Demonstration (LfD) explores techniques for learning a task policy from examples provided by a human teacher. The field of LfD has grown into an extensive body of literature over the past 30 years, with a wide variety of approaches for encoding human demonstrations and modeling skills and tasks. Additionally, we have recently seen a focus on gathering data from non-expert human teachers (i.e., domain experts but not robotics experts). In this book, we provide an introduction to the field with a focus on the unique technical challenges associated with designing robots that learn from naive human teachers. We begin, in the introduction, with a unification of the various terminology seen in the literature as well as an outline of the design choices one has in designing an LfD system. Chapter 2 gives a brief survey of the psychology literature that provides insights from human social learning that are relevant to designing robotic social learners. Chapter 3 walks through an LfD interaction, surveying the design choices one makes and state of the art approaches in prior work. First, is the choice of input, how the human teacher interacts with the robot to provide demonstrations. Next, is the choice of modeling technique. Currently, there is a dichotomy in the field between approaches that model low-level motor skills and those that model high-level tasks composed of primitive actions. We devote a chapter to each of these. Chapter 7 is devoted to interactive and active learning approaches that allow the robot to refine an existing task model. And finally, Chapter 8 provides best practices for evaluation of LfD systems, with a focus on how to approach experiments with human subjects in this domain.


Book Synopsis Robot Learning from Human Demonstration by : Sonia Dechter

Download or read book Robot Learning from Human Demonstration written by Sonia Dechter and published by Springer Nature. This book was released on 2022-06-01 with total page 109 pages. Available in PDF, EPUB and Kindle. Book excerpt: Learning from Demonstration (LfD) explores techniques for learning a task policy from examples provided by a human teacher. The field of LfD has grown into an extensive body of literature over the past 30 years, with a wide variety of approaches for encoding human demonstrations and modeling skills and tasks. Additionally, we have recently seen a focus on gathering data from non-expert human teachers (i.e., domain experts but not robotics experts). In this book, we provide an introduction to the field with a focus on the unique technical challenges associated with designing robots that learn from naive human teachers. We begin, in the introduction, with a unification of the various terminology seen in the literature as well as an outline of the design choices one has in designing an LfD system. Chapter 2 gives a brief survey of the psychology literature that provides insights from human social learning that are relevant to designing robotic social learners. Chapter 3 walks through an LfD interaction, surveying the design choices one makes and state of the art approaches in prior work. First, is the choice of input, how the human teacher interacts with the robot to provide demonstrations. Next, is the choice of modeling technique. Currently, there is a dichotomy in the field between approaches that model low-level motor skills and those that model high-level tasks composed of primitive actions. We devote a chapter to each of these. Chapter 7 is devoted to interactive and active learning approaches that allow the robot to refine an existing task model. And finally, Chapter 8 provides best practices for evaluation of LfD systems, with a focus on how to approach experiments with human subjects in this domain.

Robot Learning from Human Teachers

Robot Learning from Human Teachers

Author: Sonia Chernova

Publisher: Morgan & Claypool Publishers

Published: 2014-04-01

Total Pages: 154

ISBN-13: 1681731797

DOWNLOAD EBOOK

Learning from Demonstration (LfD) explores techniques for learning a task policy from examples provided by a human teacher. The field of LfD has grown into an extensive body of literature over the past 30 years, with a wide variety of approaches for encoding human demonstrations and modeling skills and tasks. Additionally, we have recently seen a focus on gathering data from non-expert human teachers (i.e., domain experts but not robotics experts). In this book, we provide an introduction to the field with a focus on the unique technical challenges associated with designing robots that learn from naive human teachers. We begin, in the introduction, with a unification of the various terminology seen in the literature as well as an outline of the design choices one has in designing an LfD system. Chapter 2 gives a brief survey of the psychology literature that provides insights from human social learning that are relevant to designing robotic social learners. Chapter 3 walks through an LfD interaction, surveying the design choices one makes and state of the art approaches in prior work. First, is the choice of input, how the human teacher interacts with the robot to provide demonstrations. Next, is the choice of modeling technique. Currently, there is a dichotomy in the field between approaches that model low-level motor skills and those that model high-level tasks composed of primitive actions. We devote a chapter to each of these. Chapter 7 is devoted to interactive and active learning approaches that allow the robot to refine an existing task model. And finally, Chapter 8 provides best practices for evaluation of LfD systems, with a focus on how to approach experiments with human subjects in this domain.


Book Synopsis Robot Learning from Human Teachers by : Sonia Chernova

Download or read book Robot Learning from Human Teachers written by Sonia Chernova and published by Morgan & Claypool Publishers. This book was released on 2014-04-01 with total page 154 pages. Available in PDF, EPUB and Kindle. Book excerpt: Learning from Demonstration (LfD) explores techniques for learning a task policy from examples provided by a human teacher. The field of LfD has grown into an extensive body of literature over the past 30 years, with a wide variety of approaches for encoding human demonstrations and modeling skills and tasks. Additionally, we have recently seen a focus on gathering data from non-expert human teachers (i.e., domain experts but not robotics experts). In this book, we provide an introduction to the field with a focus on the unique technical challenges associated with designing robots that learn from naive human teachers. We begin, in the introduction, with a unification of the various terminology seen in the literature as well as an outline of the design choices one has in designing an LfD system. Chapter 2 gives a brief survey of the psychology literature that provides insights from human social learning that are relevant to designing robotic social learners. Chapter 3 walks through an LfD interaction, surveying the design choices one makes and state of the art approaches in prior work. First, is the choice of input, how the human teacher interacts with the robot to provide demonstrations. Next, is the choice of modeling technique. Currently, there is a dichotomy in the field between approaches that model low-level motor skills and those that model high-level tasks composed of primitive actions. We devote a chapter to each of these. Chapter 7 is devoted to interactive and active learning approaches that allow the robot to refine an existing task model. And finally, Chapter 8 provides best practices for evaluation of LfD systems, with a focus on how to approach experiments with human subjects in this domain.

Robot Learning Human Skills and Intelligent Control Design

Robot Learning Human Skills and Intelligent Control Design

Author: CHENGUANG. YANG

Publisher: CRC Press

Published: 2023-09-25

Total Pages: 0

ISBN-13: 9780367634377

DOWNLOAD EBOOK

This book focusses on robotic skill learning and intelligent control for robotic manipulators including enabling of robots to efficiently learn motor and stiffness/force regulation policies from humans. It explains transfer of human limb impedance control strategies to the robots so that the adaptive impedance control for the robot can be realized.


Book Synopsis Robot Learning Human Skills and Intelligent Control Design by : CHENGUANG. YANG

Download or read book Robot Learning Human Skills and Intelligent Control Design written by CHENGUANG. YANG and published by CRC Press. This book was released on 2023-09-25 with total page 0 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book focusses on robotic skill learning and intelligent control for robotic manipulators including enabling of robots to efficiently learn motor and stiffness/force regulation policies from humans. It explains transfer of human limb impedance control strategies to the robots so that the adaptive impedance control for the robot can be realized.

Deep Reinforcement Learning

Deep Reinforcement Learning

Author: Hao Dong

Publisher: Springer Nature

Published: 2020-06-29

Total Pages: 526

ISBN-13: 9811540950

DOWNLOAD EBOOK

Deep reinforcement learning (DRL) is the combination of reinforcement learning (RL) and deep learning. It has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine, and famously contributed to the success of AlphaGo. Furthermore, it opens up numerous new applications in domains such as healthcare, robotics, smart grids and finance. Divided into three main parts, this book provides a comprehensive and self-contained introduction to DRL. The first part introduces the foundations of deep learning, reinforcement learning (RL) and widely used deep RL methods and discusses their implementation. The second part covers selected DRL research topics, which are useful for those wanting to specialize in DRL research. To help readers gain a deep understanding of DRL and quickly apply the techniques in practice, the third part presents mass applications, such as the intelligent transportation system and learning to run, with detailed explanations. The book is intended for computer science students, both undergraduate and postgraduate, who would like to learn DRL from scratch, practice its implementation, and explore the research topics. It also appeals to engineers and practitioners who do not have strong machine learning background, but want to quickly understand how DRL works and use the techniques in their applications.


Book Synopsis Deep Reinforcement Learning by : Hao Dong

Download or read book Deep Reinforcement Learning written by Hao Dong and published by Springer Nature. This book was released on 2020-06-29 with total page 526 pages. Available in PDF, EPUB and Kindle. Book excerpt: Deep reinforcement learning (DRL) is the combination of reinforcement learning (RL) and deep learning. It has been able to solve a wide range of complex decision-making tasks that were previously out of reach for a machine, and famously contributed to the success of AlphaGo. Furthermore, it opens up numerous new applications in domains such as healthcare, robotics, smart grids and finance. Divided into three main parts, this book provides a comprehensive and self-contained introduction to DRL. The first part introduces the foundations of deep learning, reinforcement learning (RL) and widely used deep RL methods and discusses their implementation. The second part covers selected DRL research topics, which are useful for those wanting to specialize in DRL research. To help readers gain a deep understanding of DRL and quickly apply the techniques in practice, the third part presents mass applications, such as the intelligent transportation system and learning to run, with detailed explanations. The book is intended for computer science students, both undergraduate and postgraduate, who would like to learn DRL from scratch, practice its implementation, and explore the research topics. It also appeals to engineers and practitioners who do not have strong machine learning background, but want to quickly understand how DRL works and use the techniques in their applications.