Grokking Deep Reinforcement Learning

Grokking Deep Reinforcement Learning uses engaging exercises to teach you how to build deep learning systems. This book combines annotated Python code with intuitive explanations to explore DRL techniques. Youll see how algorithms function and learn to develop your own DRL agents using evaluative feedback. Summary We all learn through trial and error. We avoid the things that cause us to experience pain and failure. We embrace and build on the things that give us reward and success. This common pattern is the foundation of deep reinforcement learning: building machine learning systems that explore and learn based on the responses of the environment. Grokking Deep Reinforcement Learning introduces this powerful machine learning approach, using examples, illustrations, exercises, and crystal-clear teaching. You'll love the perfectly paced teaching and the clever, engaging writing style as you dig into this awesome exploration of reinforcement learning fundamentals, effective deep learning techniques, and practical applications in this emerging field. Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications. About the technology We learn by interacting with our environment, and the rewards or punishments we experience guide our future behavior. Deep reinforcement learning brings that same natural process to artificial intelligence, analyzing results to uncover the most efficient ways forward. DRL agents can improve marketing campaigns, predict stock performance, and beat grand masters in Go and chess. About the book Grokking Deep Reinforcement Learning uses engaging exercises to teach you how to build deep learning systems. This book combines annotated Python code with intuitive explanations to explore DRL techniques. Youll see how algorithms function and learn to develop your own DRL agents using evaluative feedback. What's inside An introduction to reinforcement learning DRL agents with human-like behaviors Applying DRL to complex situations About the reader For developers with basic deep learning experience. About the author Miguel Morales works on reinforcement learning at Lockheed Martin and is an instructor for the Georgia Institute of Technologys Reinforcement Learning and Decision Making course. Table of Contents 1 Introduction to deep reinforcement learning 2 Mathematical foundations of reinforcement learning 3 Balancing immediate and long-term goals 4 Balancing the gathering and use of information 5 Evaluating agents behaviors 6 Improving agents behaviors 7 Achieving goals more effectively and efficiently 8 Introduction to value-based deep reinforcement learning 9 More stable value-based methods 10 Sample-efficient value-based methods 11 Policy-gradient and actor-critic methods 12 Advanced actor-critic methods 13 Toward artificial general intelligence foreword preface acknowledgments about this book about the author Introduction todeep reinforcement learning What is deep reinforcement learning? The past, present, and future of deep reinforcement learning The suitability of deep reinforcement learning Setting clear two-way expectations Mathematical foundationsof reinforcement learning Components of reinforcement learning MDPs: The engine of the environment Balancing immediateand long-term goals The objective of a decision-making agent Planning optimal sequences of actions Balancing the gatheringand use of information The challenge of interpreting evaluative feedback Strategic exploration Evaluatingagents’ behaviors Learning to estimate the value of policies Learning to estimate from multiple steps Improvingagents’ behaviors The anatomy of reinforcement learning agents Learning to improve policies of behavior Decoupling behavior from learning Achieving goals moreeffectively and efficiently Learning to improve policies using robust targets Agents that interact, learn, and plan Introduction to value-baseddeep reinforcement learning The kind of feedback deep reinforcement learning agents use Introduction to function approximation for reinforcement learning NFQ: The first attempt at value-based deep reinforcement learning More stablevalue-based methods DQN: Making reinforcement learning more like supervised learning Double DQN: Mitigating the overestimation of action-value functions Sample-efficientvalue-based methods Dueling DDQN: A reinforcement-learning-aware neural network architecture PER: Prioritizing the replay of meaningful experiences Policy-gradient andactor-critic methods REINFORCE: Outcome-based policy learning VPG: Learning a value function A3C: Parallel policy updates GAE: Robust advantage estimation A2C: Synchronous policy updates Advancedactor-critic methods DDPG: Approximating a deterministic policy TD3: State-of-the-art improvements over DDPG SAC: Maximizing the expected return and entropy PPO: Restricting optimization steps Toward artificialgeneral intelligence What was covered and what notably wasn’t? More advanced concepts toward AGI What happens next? index