Key FeaturesTake your machine learning skills to the next level with reinforcement learning techniquesBuild automated decision-making capabilities in your systemsCover Reinforcement Learning concepts, frameworks, algorithms, and more in detailBook DescriptionReinforcement learning (RL) is becoming a popular tool for constructing autonomous systems that can improve themselves with experience. We will break the RL framework into its core building blocks, and provide you with details of each element.This book aims to strengthen your machine learning skills by acquainting you with reinforcement learning algorithms and techniques. This book is divided into three parts. The first part defines Reinforcement Learning and describes its basics. It also covers the basics of Python and Java frameworks, which we are going to use later in the book. The second part discusses learning techniques with basic algorithms such as Temporal Difference, Monte Carlo, and Policy Gradient—all with practical examples. Lastly, in the third part we apply Reinforcement Learning with the most recent and widely used algorithms via practical applications.By the end of this book, youll know the practical implementation of case studies and current research activities to help you advance further with Reinforcement Learning.What you will learnUnderstand the basics of reinforcement learning methods, algorithms, and more, and the differences between supervised, unsupervised, and reinforcement learningMaster the Markov Decision Process math framework by building an OO-MDP Domain in JavaLearn dynamic programming principles and the implementation of Fibonacci computation in JavaUnderstand Python implementation of temporal difference learningDevelop Monte Carlo methods and various policies used to build a Monte Carlo simulator using PythonUnderstand Policy Gradient methods and policies applied in the reinforcement domainInstill reinforcement methods in the autonomous platform using a moving car exampleApply reinforcement learning algorithms in games with REINFORCEjsAbout the AuthorDr. Engr. S.M. Farrukh Akhtar is an active researcher and speaker with more than 13 years of industrial experience analyzing, designing, developing, integrating, and managing large applications in different countries and diverse industries. He has worked in Dubai, Pakistan, Germany, Singapore, and Malaysia. He is currently working in Hewlett Packard as an enterprise solution architect.He received a PhD in artificial intelligence from European Global School, France. He also received two masters degrees: a masters of intelligent systems from the University Technology Malaysia, and MBA in business strategy from the International University of Georgia. Farrukh completed his BSc in computer engineering from Sir Syed University of Engineering and Technology, Pakistan. He is also an active contributor and member of the machine learning for data science research group in the University Technology Malaysia. His research and focus areas are mainly big data, deep learning, and reinforcement learning.He has cross-platform expertise and has achieved recognition for his expertise from IBM, Sun Microsystems, Oracle, and Microsoft. Farrukh received the following accolades:Sun Certified Java Programmer in 2001Microsoft Certified Professional and Sun Certified Web Component Developer in 2002Microsoft Certified Application Developer in 2003Microsoft Certified Solution Developer in 2004Oracle Certified Professional in 2005IBM Certified Solution Developer - XML in 2006IBM Certified Big Data Architect and Scrum Master Certified - For Agile Software Practitioners in 2017He also contributes his experience and services as a member of the board of directors in K.K. Abdal Institute of Engineering and Management Sciences, Pakistan, and is a board member of Alam Educational Society.Table of ContentsReinforcement LearningMarkov decision ProcessDynamic programmingTemporal Difference LearningMonte Carlo MethodsLearning and planningDeep Reinforcement learningGame TheoryReinforcement learning showdownApplications and Case Studies: Reinforcement LearningCurrent Research - Reinforcement Learning