舉報 
會員
Keras Reinforcement Learning Projects
ReinforcementlearninghasevolvedalotinthelastcoupleofyearsandproventobeasuccessfultechniqueinbuildingsmartandintelligentAInetworks.KerasReinforcementLearningProjectsinstallshuman-levelperformanceintoyourapplicationsusingalgorithmsandtechniquesofreinforcementlearning,coupledwithKeras,afasterexperimentallibrary.ThebookbeginswithgettingyouupandrunningwiththeconceptsofreinforcementlearningusingKeras.You’lllearnhowtosimulatearandomwalkusingMarkovchainsandselectthebestportfoliousingdynamicprogramming(DP)andPython.You’llalsoexploreprojectssuchasforecastingstockpricesusingMonteCarlomethods,deliveringvehicleroutingapplicationusingTemporalDistance(TD)learningalgorithms,andbalancingaRotatingMechanicalSystemusingMarkovdecisionprocesses.Onceyou’veunderstoodthebasics,you’llmoveontoModelingofaSegway,runningarobotcontrolsystemusingdeepreinforcementlearning,andbuildingahandwrittendigitrecognitionmodelinPythonusinganimagedataset.Finally,you’llexcelinplayingtheboardgameGowiththehelpofQ-Learningandreinforcementlearningalgorithms.Bytheendofthisbook,you’llnotonlyhavedevelopedhands-ontrainingonconcepts,algorithms,andtechniquesofreinforcementlearningbutalsobeallsettoexploretheworldofAI.
目錄(172章)
倒序
- 封面
- Title Page
- Copyright and Credits
- Keras Reinforcement Learning Projects
- Packt Upsell
- Why subscribe?
- Packt.com
- Contributors
- About the author
- About the reviewer
- Packt is searching for authors like you
- Preface
- Who this book is for
- What this book covers
- To get the most out of this book
- Download the example code files
- Download the color images
- Conventions used
- Get in touch
- Reviews
- Overview of Keras Reinforcement Learning
- Basic concepts of machine learning
- Discovering the different types of machine learning
- Supervised learning
- Unsupervised learning
- Reinforcement learning
- Building machine learning models step by step
- Getting started with reinforcement learning
- Agent-environment interface
- Markov Decision Process
- Discounted cumulative reward
- Exploration versus exploitation
- Reinforcement learning algorithms
- Dynamic Programming
- Monte Carlo methods
- Temporal difference learning
- SARSA
- Q-learning
- Deep Q-learning
- Summary
- Simulating Random Walks
- Random walks
- One-dimensional random walk
- Simulating 1D random walk
- Markov chains
- Stochastic process
- Probability calculation
- Markov chain definition
- Transition matrix
- Transition diagram
- Weather forecasting with Markov chains
- Generating pseudorandom text with Markov chains
- Summary
- Optimal Portfolio Selection
- Dynamic Programming
- Divide and conquer versus Dynamic Programming
- Memoization
- Dynamic Programming in reinforcement-learning applications
- Optimizing a financial portfolio
- Optimization techniques
- Solving the knapsack problem using Dynamic Programming
- Different approaches to the problem
- Brute force
- Greedy algorithms
- Dynamic Programming
- Summary
- Forecasting Stock Market Prices
- Monte Carlo methods
- Historical background
- Basic concepts of the Monte Carlo simulation
- Monte Carlo applications
- Numerical integration using the Monte Carlo method
- Monte Carlo for prediction and control
- Amazon stock price prediction using Python
- Exploratory analysis
- The Geometric Brownian motion model
- Monte Carlo simulation
- Summary
- Delivery Vehicle Routing Application
- Temporal difference learning
- SARSA
- Q-learning
- Basics of graph theory
- The adjacency matrix
- Adjacency lists
- Graphs as data structures in Python
- Graphs using the NetworkX package
- Finding the shortest path
- The Dijkstra algorithm
- The Dijkstra algorithm using the NetworkX package
- The Google Maps algorithm
- The Vehicle Routing Problem
- Summary
- Continuous Balancing of a Rotating Mechanical System
- Neural network basic concepts
- The Keras neural network model
- Classifying breast cancer using the neural network
- Deep reinforcement learning
- The Keras–RL package
- Continuous control with deep reinforcement learning
- Summary
- Dynamic Modeling of a Segway as an Inverted Pendulum System
- How Segways work
- System modeling basics
- OpenAI Gym
- OpenAI Gym methods
- OpenAI Gym installation
- The CartPole system
- Q-learning solution
- Deep Q-learning solution
- Summary
- Robot Control System Using Deep Reinforcement Learning
- Robot control
- Robotics overview
- Robot evolution
- First-generation robots
- Second-generation robots
- Third-generation robots
- Fourth-generation robots
- Robot autonomy
- Robot mobility
- Automatic control
- Control architectures
- The FrozenLake environment
- The Q-learning solution
- A Deep Q-learning solution
- Summary
- Handwritten Digit Recognizer
- Handwritten digit recognition
- Optical Character Recognition
- Computer vision
- Handwritten digit recognition using an autoencoder
- Loading data
- Model architecture
- Deep autoencoder Q-learning
- Summary
- Playing the Board Game Go
- Game theory
- Basic concepts
- Game types
- Cooperative games
- Symmetrical games
- Zero-sum games
- Sequential games
- Game theory applications
- Prisoner's dilemma
- Stag hunt
- Chicken game
- The Go game
- Basic rules of the game
- Scoring rules
- The AlphaGo project
- The AlphaGo algorithm
- Monte Carlo Tree Search
- Convolutional networks
- Summary
- What's Next?
- Reinforcement-learning applications in real life
- DeepMind AlphaZero
- IBM Watson
- The Unity Machine Learning Agents toolkit
- FANUC industrial robots
- Automated trading systems using reinforcement learning
- Next steps for reinforcement learning
- Inverse reinforcement learning
- Learning by demonstration
- Deep Deterministic Policy Gradients
- Reinforcement learning from human preferences
- Hindsight Experience Replay
- Summary
- Other Books You May Enjoy
- Leave a review - let other readers know what you think 更新時間：2021-08-13 15:26:40
推薦閱讀
- Hands-On Graph Analytics with Neo4j
- Unreal Engine：Game Development from A to Z
- 大數據技術基礎
- 精通MATLAB圖像處理
- 21天學通PHP
- Learning Apache Cassandra（Second Edition）
- 運動控制器與交流伺服系統的調試和應用
- 悟透AutoCAD 2009完全自學手冊
- Chef：Powerful Infrastructure Automation
- 在實戰中成長：Windows Forms開發之路
- 手機游戲策劃設計
- 電腦上網入門
- Unreal Development Kit Game Design Cookbook
- 從機器學習到無人駕駛
- Mastering Microsoft Dynamics 365 Customer Engagement
- 信息技術基礎應用
- Arduino創意機器人入門：基于Mixly
- 數據庫技術：Access 2003·計算機網絡技術
- MATLAB寶典
- 機器人學基礎
- 圖解變頻器維修
- Web性能權威指南
- 游戲外掛攻防藝術
- Big Data Architect’s Handbook
- Data Science for Marketing Analytics
- Mobile Game Design Essentials
- 信息系統安全
- 機器學習從入門到入職：用sklearn與keras搭建人工智能模型
- 深度學習實戰
- 玩轉智能機器人mBot Ranger：搭建與編程
