Summary  Humans learn best from feedback8212we are encouraged to take actions that lead to positive results while deterred by decisions with negative consequences. This reinforcement process can be applied to computer programs allowing them to solve more complex problems that classical programming cannot. Deep Reinforcement Learning in Action teaches you the fundamental concepts and terminology of deep reinforcement learning, along with the practical skills and techniques you8217ll need to implement it into your own projects.  Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.  About the technology  Deep reinforcement learning AI systems rapidly adapt to new environments, a vast improvement over standard neural networks. A DRL agent learns like people do, taking in raw data such as sensor input and refining its responses and predictions through trial and error.  About the book  Deep Reinforcement Learning in Action teaches you how to program AI agents that adapt and improve based on direct feedback from their environment. In this example-rich tutorial, you8217ll master foundational and advanced DRL techniques by taking on interesting challenges like navigating a maze and playing video games. Along the way, you8217ll work with core algorithms, including deep Q-networks and policy gradients, along with industry-standard tools like PyTorch and OpenAI Gym.  What's inside  nbspnbspnbsp Building and training DRL networks nbspnbspnbsp The most popular DRL algorithms for learning and problem solving nbspnbspnbsp Evolutionary algorithms for curiosity and multi-agent learning nbspnbspnbsp All examples available as Jupyter Notebooks  About the reader  For readers with intermediate skills in Python and deep learning.  About the author  Alexander Zai is a machine learning engineer at Amazon AI. Brandon Brown is a machine learning and data analysis blogger.  Table of Contents  PART 1 - FOUNDATIONS  1. What is reinforcement learning?  2. Modeling reinforcement learning problems: Markov decision processes  3. Predicting the best states and actions: Deep Q-networks  4. Learning to pick the best policy: Policy gradient methods  5. Tackling more complex problems with actor-critic methods  PART 2 - ABOVE AND BEYOND  6. Alternative optimization methods: Evolutionary algorithms  7. Distributional DQN: Getting the full story  8.Curiosity-driven exploration  9. Multi-agent reinforcement learning  10. Interpretable reinforcement learning: Attention and relational models  11. In conclusion: A review and roadmap  nbsp