Delve into the world of reinforcement learning algorithms and apply them to different use-cases via Python. This book covers important topics such as policy gradients and Q learning, and utilizes frameworks such as Tensorflow, Keras, and OpenAI Gym. Applied Reinforcement Learning with Python introduces you to the theory behind reinforcement learning (RL) algorithms and the code that will be used to implement them. You will take a guided tour through features of OpenAI Gym, from utilizing standard libraries to creating your own environments, then discover how to frame reinforcement learning problems so you can research, develop, and deploy RL-based solutions. What You'll Learn Implement reinforcement learning with Python Work with AI frameworks such as OpenAI Gym, Tensorflow, and Keras Deploy and train reinforcement learning-based solutions via cloud resources Apply practical applications of reinforcement learning Who This Book Is For Data scientists, machine learning engineers and software engineers familiar with machine learning and deep learning concepts.;Intro; Table of Contents; About the Author; About the Technical Reviewer; Acknowledgments; Introduction; Chapter 1: Introduction to Reinforcement Learning; History of Reinforcement Learning; MDPs and their Relation to Reinforcement Learning; Reinforcement Learning Algorithms and RL Frameworks; Q Learning; Actor-Critic Models; Applications of Reinforcement Learning; Classic Control Problems; Super Mario Bros.; Doom; Reinforcement-Based Marketing Making; Sonic the Hedgehog; Conclusion; Chapter 2: Reinforcement Learning Algorithms; OpenAI Gym; Policy-Based Learning Intro Table of Contents About the Author About the Technical Reviewer Acknowledgments Introduction Chapter 1: Introduction to Reinforcement Learning History of Reinforcement Learning MDPs and their Relation to Reinforcement Learning Reinforcement Learning Algorithms and RL Frameworks Q Learning Actor-Critic Models Applications of Reinforcement Learning Classic Control Problems Super Mario Bros. Doom Reinforcement-Based Marketing Making Sonic the Hedgehog Conclusion Chapter 2: Reinforcement Learning Algorithms OpenAI Gym Policy-Based Learning Policy Gradients Explained MathematicallyGradient Ascent Applied to Policy Optimization Using Vanilla Policy Gradients on the Cart Pole Problem What Are Discounted Rewards and Why Do We Use Them? Drawbacks to Policy Gradients Proximal Policy Optimization (PPO) and Actor-Critic Models Implementing PPO and Solving Super Mario Bros. Overview of Super Mario Bros. Installing Environment Package Structure of the Code in Repository Model Architecture Working with a More Difficult Reinforcement Learning Challenge Dockerizing Reinforcement Learning Experiments Results of the Experiment ConclusionChapter 3: Reinforcement Learning Algorithms: Q Learning and Its Variants Q Learning Temporal Difference (TD) Learning Epsilon-Greedy Algorithm Frozen Lake Solved with Q Learning Deep Q Learning Playing Doom with Deep Q Learning Simple Doom Level Training and Performance Limitations of Deep Q Learning Double Q Learning and Double Deep Q Networks Conclusion Chapter 4: Market Making via Reinforcement Learning What Is Market Making? Trading Gym Why Reinforcement Learning for This Problem? Synthesizing Order Book Data with Trading Gym Generating Order Book Data with Trading GymExperimental Design RL Approach 1: Policy Gradients RL Approach 2: Deep Q Network Results and Discussion Conclusion Chapter 5: Custom OpenAI Reinforcement Learning Environments Overview of Sonic the Hedgehog Downloading the Game Writing the Code for the Environment A3C Actor-Critic Conclusion Appendix A: Source Code Market Making Model Utilities Policy Gradient Utilities Models Chapter 1 OpenAI Example Chapter 2 Cart Pole Example Super Mario Example Chapter 3 Frozen Lake Example Doom Example Chapter 4 Market Making Example Chapter 5Sonic Example Index Delve into the world of reinforcement learning algorithms and apply them to different use-cases via Python. This book covers important topics such as policy gradients and Q learning, and utilizes frameworks such as Tensorflow, Keras, and OpenAI Gym. __**Applied Reinforcement Learning with Python**__ introduces you to the theory behind reinforcement learning (RL) algorithms and the code that will be used to implement them. You will take a guided tour through features of OpenAI Gym, from utilizing standard libraries to creating your own environments, then discover how to frame reinforcement learning problems so you can research, develop, and deploy RL-based solutions. **What You'll Learn** * Implement reinforcement learning with Python * Work with AI frameworks such as OpenAI Gym, Tensorflow, and Keras * Deploy and train reinforcement learning–based solutions via cloud resources * Apply practical applications of reinforcement learning **Who This Book Is For** Data scientists, machine learning engineers and software engineers familiar with machine learning and deep learning concepts.
