Python Reinforcement Learning : Solve complex real-world problems by mastering reinforcement learning algorithms using OpenAI Gym and TensorFlow /: Solve complex real-world problems by mastering reinforcement learning algorithms using OpenAI Gym and TensorFlow. (2019)

• Record Type: Book
• Further Information: Note: Sudharsan Ravichandiran, Sean Saito, Rajalingappaa Shanmugamani, Yang Wenzhuo.
• Authors: Ravichandiran, Sudharsan; Saito, Sean; Shanmugamani, Rajalingappaa; Wenzhuo, Yang
• Contents: Table of ContentsIntroduction to Reinforcement LearningGetting Started with OpenAI and TensorFlowThe Markov Decision Process and Dynamic ProgrammingGaming with Monte Carlo MethodsTemporal Difference LearningMulti-Armed Bandit ProblemPlaying Atari GamesAtari Games with Deep Q NetworkPlaying Doom with a Deep Recurrent Q NetworkThe Asynchronous Advantage Actor Critic NetworkPolicy Gradients and OptimizationBalancing CartPoleSimulating Control TasksBuilding Virtual Worlds in MinecraftLearning to Play GoCreating a ChatbotGenerating a Deep Learning Image ClassifierPredicting Future Stock PricesCapstone Project - Car Racing Using DQNLooking Ahead.
• Publisher Details: Birmingham : Packt Publishing
• Publication Date: 2019
• Extent: 1 online resource (496 pages)
• Subjects: Computers -- Intelligence (AI) & Semantics; Computers -- Information Technology; Information technology: general issues; Artificial intelligence; Computers -- Neural Networks; Neural networks & fuzzy systems
• Languages: English
• ISBNs: 9781838640149; 1838640142
• Related ISBNs: 9781838649777
• Access Rights: Legal Deposit; Only available on premises controlled by the deposit library and to one user at any one time; The Legal Deposit Libraries (Non-Print Works) Regulations (UK).
• Access Usage: Restricted: Printing from this resource is governed by The Legal Deposit Libraries (Non-Print Works) Regulations (UK) and UK copyright law currently in force.