Practical Reinforcement Learning

Dr. Engr. S.M. Farrukh Akhtar

  • 出版商: Packt Publishing
  • 出版日期: 2017-10-17
  • 售價: $2,100
  • 貴賓價: 9.5$1,995
  • 語言: 英文
  • 頁數: 336
  • 裝訂: Paperback
  • ISBN: 1787128725
  • ISBN-13: 9781787128729
  • 相關分類: ReinforcementDeepLearning
  • 無法訂購

買這商品的人也買了...

商品描述

Master different reinforcement learning techniques and their practical implementation using OpenAI Gym, Python and Java

About This Book

  • Take your machine learning skills to the next level with reinforcement learning techniques
  • Build automated decision-making capabilities in your systems
  • Cover Reinforcement Learning concepts, frameworks, algorithms, and more in detail

Who This Book Is For

Machine learning/AI practitioners, data scientists, data analysts, machine learning engineers, and developers who are looking to expand their existing knowledge to build optimized machine learning models, will find this book very useful.

What You Will Learn

  • Understand the basics of reinforcement learning methods, algorithms, and more, and the differences between supervised, unsupervised, and reinforcement learning
  • Master the Markov Decision Process math framework by building an OO-MDP Domain in Java
  • Learn dynamic programming principles and the implementation of Fibonacci computation in Java
  • Understand Python implementation of temporal difference learning
  • Develop Monte Carlo methods and various policies used to build a Monte Carlo simulator using Python
  • Understand Policy Gradient methods and policies applied in the reinforcement domain
  • Instill reinforcement methods in the autonomous platform using a moving car example
  • Apply reinforcement learning algorithms in games with REINFORCEjs

In Detail

Reinforcement 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, you'll know the practical implementation of case studies and current research activities to help you advance further with Reinforcement Learning.

Style and approach

This hands-on book will further expand your machine learning skills by teaching you the different reinforcement learning algorithms and techniques using practical examples.

商品描述(中文翻譯)

掌握不同的強化學習技術及其在OpenAI Gym、Python和Java中的實際應用。

關於本書:
- 透過強化學習技術提升您的機器學習能力。
- 在系統中建立自動化的決策能力。
- 詳細介紹強化學習的概念、框架、演算法等。

本書適合對象:
- 機器學習/人工智慧從業人員、資料科學家、資料分析師、機器學習工程師和開發人員,希望擴展現有知識以建立優化的機器學習模型。

學習內容:
- 瞭解強化學習方法、演算法等基礎知識,以及監督式學習、非監督式學習和強化學習之間的差異。
- 通過在Java中建立OO-MDP領域,掌握馬可夫決策過程數學框架。
- 學習動態規劃原則,並在Java中實現費波那契計算。
- 瞭解Python實現的時序差異學習。
- 開發蒙特卡羅方法和各種策略,使用Python構建蒙特卡羅模擬器。
- 瞭解強化學習領域中應用的策略梯度方法和策略。
- 通過移動汽車示例,在自主平台中實施強化方法。
- 在遊戲中應用強化學習算法,使用REINFORCEjs。

詳細內容:
強化學習(RL)正成為構建能夠通過經驗改進自身的自主系統的流行工具。我們將將RL框架拆分為其核心組件,並為您提供每個元素的詳細信息。

本書旨在通過介紹強化學習算法和技術來增強您的機器學習能力。本書分為三個部分。第一部分定義了強化學習並描述了其基礎知識。它還涵蓋了Python和Java框架的基礎知識,這些知識將在本書後面使用。第二部分討論了具有基本算法(如時序差異、蒙特卡羅和策略梯度)的學習技術,並提供實際示例。最後,在第三部分中,我們通過實際應用程序使用最新和廣泛使用的強化學習算法。

通過閱讀本書,您將了解案例研究的實際實施和當前研究活動,以幫助您在強化學習方面更進一步。

風格和方法:
本書通過實際示例教授不同的強化學習算法和技術,進一步擴展您的機器學習能力。