Master various reinforcement learning algorithms by building intelligent self-evolving applications using state-of-the-art deep reinforcement learning architecturesKey FeaturesYour entry point into the world of artificial intelligence with the power of PythonExample-rich guide to learn reinforcement learning concepts, frameworks, and algorithms to build smart, interactive, and self-evolving modelsExplore deep neural networks and other differentiable models such as RNN, CNN, and LSTM networks with TensorFlow, OpenAI, and KerasBook DescriptionReinforcement Learning with Python will take your learning to the next level. It will help you master the concepts of reinforcement learning to deep reinforcement learning and you will see things in action. The book will explain everything from scratch by implementing practical applications at work or projects, all written in Python.The book starts with an introduction to Reinforcement Learning, OpenAI, and TensorFlow. You will then explore Reinforcement learning algorithms and concepts such as the Markov Decision Processes (MDPs), Monte-Carlo tree search, and dynamic programming, including policy and value iteration. You will get to grips with temporal difference learning algorithms, including Q-learning and SARSA. This example-rich guide will introduce you to neural networks and deep learning, covering various deep learning algorithms. You will explore deep reinforcement learning in depth, which is a combination of deep learning and reinforcement learning. You will also learn how deep reinforcement learning algorithms can be used with TensorFlow and Keras to build intelligent applications.By the end of the book, you will have all the knowledge and experience to implement reinforcement learning and deep reinforcement learning in your projects, and you will be all set to enter the world of artificial intelligence.What you will learnUnderstand the basics of reinforcement learning methods, algorithms, and elementsLearn how to build a video game bot using OpenAI Gym and UniverseUnderstand the Markov Decision Process and Bellman's optimalitySolve FrozenLake problems using dynamic programmingDevelop an agent to play tic-tac-toe game using Monte Carlo Tree SearchBuild intelligent games using Q-learning and SarsaLearn to solve Multi-armed bandit problems using policy gradientsUnderstand deep learning algorithms and reinforcement learning context of deep learningBuild state-of-the-art architectures such as DQN, DRQN, PPO, and TRPOPerform sentiment analysis using Deep Q LearningMaster actor-critic algorithms by building an unbeatable Doom gameBuild a self-driving car using DRL algorithmsWho This Book Is ForIf you're a machine learning developer or deep learning enthusiast who is interested in artificial intelligence and want to learn about reinforcement learning from scratch, then this book is for you. You can become a reinforcement learning expert by implementing practical examples at work or projects. Having some knowledge of linear algebra, statistics, and the Python programming language will help you understand the flow of the book.
Author: Sudharsan Ravichandiran