What this book covers
Chapter 1, What is Reinforcement Learning?, contains introduction to RL ideas and main formal models.
Chapter 2, OpenAI Gym, introduces the reader to the practical aspect of RL, using open-source library gym.
Chapter 3, Deep Learning with PyTorch, gives a quick overview of the PyTorch library.
Chapter 4, The Cross-Entropy Method, introduces you to one of the simplest methods of RL to give you the feeling of RL methods and problems.
Chapter 5, Tabular Learning and the Bellman Equation, gives an introduction to the Value-based family of RL methods.
Chapter 6, Deep Q-Networks, describes DQN, the extension of basic Value-based methods, allowing to solve complicated environment.
Chapter 7, DQN Extensions, gives a detailed overview of modern extension to the DQN method, to improve its stability and convergence in complex environments.
Chapter 8, Stocks Trading Using RL, is the first practical project, applying the DQN method to stock trading.
Chapter 9, Policy Gradients – An Alternative, introduces another family of RL methods, based on policy learning.
Chapter 10, The Actor-Critic Method, describes one of the most widely used method in RL.
Chapter 11, Asynchronous Advantage Actor-Critic, extends Actor-Critic with parallel environment communication, to improve stability and convergence.
Chapter 12, Chatbots Training with RL, is the second project, showing how to apply RL methods to NLP problems.
Chapter 13, Web Navigation, is another long project, applying RL to web page navigation, using MiniWoB set of tasks.
Chapter 14, Continuous Action Space, describes the specifics of environments, using continuous action spaces and various methods.
Chapter 15, Trust Regions – TRPO, PPO, and ACKTR, is yet another chapter about continuous action spaces describing "Trust region" set of methods.
Chapter 16, Black-Box Optimization in RL, shows another set of methods that don't use gradients in explicit form.
Chapter 17, Beyond Model-Free – Imagination, introduces model-based approach to RL, using recent research results about imagination in RL.
Chapter 18, AlphaGo Zero, describes the AlphaGo Zero method applied to game Connect Four.
