{"product_id":"9781617295430","title":"Deep Reinforcement Learning in Action","description":"Summary\u003cbr\u003e \u003cbr\u003e Humans learn best from feedback—we 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. \u003ci\u003eDeep Reinforcement Learning in Action\u003c\/i\u003e teaches you the fundamental concepts and terminology of deep reinforcement learning, along with the practical skills and techniques you’ll need to implement it into your own projects.\u003cbr\u003e \u003cbr\u003e Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.\u003cbr\u003e \u003cbr\u003e About the technology\u003cbr\u003e \u003cbr\u003e 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.\u003cbr\u003e \u003cbr\u003e About the book\u003cbr\u003e \u003cbr\u003e \u003ci\u003eDeep Reinforcement Learning in Action\u003c\/i\u003e teaches you how to program AI agents that adapt and improve based on direct feedback from their environment. In this example-rich tutorial, you’ll master foundational and advanced DRL techniques by taking on interesting challenges like navigating a maze and playing video games. Along the way, you’ll work with core algorithms, including deep Q-networks and policy gradients, along with industry-standard tools like PyTorch and OpenAI Gym.\u003cbr\u003e \u003cbr\u003e What's inside\u003cbr\u003e \u003cbr\u003e     Building and training DRL networks\u003cbr\u003e     The most popular DRL algorithms for learning and problem solving\u003cbr\u003e     Evolutionary algorithms for curiosity and multi-agent learning\u003cbr\u003e     All examples available as Jupyter Notebooks\u003cbr\u003e \u003cbr\u003e About the reader\u003cbr\u003e \u003cbr\u003e For readers with intermediate skills in Python and deep learning.\u003cbr\u003e \u003cbr\u003e About the author\u003cbr\u003e \u003cbr\u003e \u003cb\u003eAlexander Zai\u003c\/b\u003e is a machine learning engineer at Amazon AI. \u003cb\u003eBrandon Brown\u003c\/b\u003e is a machine learning and data analysis blogger.\u003cbr\u003e \u003cbr\u003e Table of Contents\u003cbr\u003e \u003cbr\u003e PART 1 - FOUNDATIONS\u003cbr\u003e \u003cbr\u003e 1. What is reinforcement learning?\u003cbr\u003e \u003cbr\u003e 2. Modeling reinforcement learning problems: Markov decision processes\u003cbr\u003e \u003cbr\u003e 3. Predicting the best states and actions: Deep Q-networks\u003cbr\u003e \u003cbr\u003e 4. Learning to pick the best policy: Policy gradient methods\u003cbr\u003e \u003cbr\u003e 5. Tackling more complex problems with actor-critic methods\u003cbr\u003e \u003cbr\u003e PART 2 - ABOVE AND BEYOND\u003cbr\u003e \u003cbr\u003e 6. Alternative optimization methods: Evolutionary algorithms\u003cbr\u003e \u003cbr\u003e 7. Distributional DQN: Getting the full story\u003cbr\u003e \u003cbr\u003e 8.Curiosity-driven exploration\u003cbr\u003e \u003cbr\u003e 9. Multi-agent reinforcement learning\u003cbr\u003e \u003cbr\u003e 10. Interpretable reinforcement learning: Attention and relational models\u003cbr\u003e \u003cbr\u003e 11. In conclusion: A review and roadmap\u003cbr\u003e \u003cbr\u003e","brand":"Manning","offers":[{"title":"Default Title","offer_id":42466525216829,"sku":"9781617295430","price":49.99,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0603\/0838\/9949\/files\/9781617295430_p0.jpg?v=1771577821","url":"https:\/\/www.tatteredcover.com\/products\/9781617295430","provider":"Tattered Cover","version":"1.0","type":"link"}