Comprehensive guide to reinforcement learning algorithms, covering dynamic programming, temporal difference, Monte-Carlo methods, and more. Suitable for researchers, students, and practitioners in AI, ML, and control engineering.
Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a long-term objective. This book focuses on those algorithms of reinforcement learning that build on the powerful theory of dynamic programming, providing a comprehensive catalog of learning problems and describing the core ideas together with a large number of state-of-the-art algorithms, followed by the discussion of their theoretical properties and limitations.
This course is recommended for anyone interested in reinforcement learning, including researchers, students, and practitioners in the fields of artificial intelligence, machine learning, and control engineering. It provides a solid foundation in the theory and practice of reinforcement learning, and is suitable for both beginners and advanced learners.
Learn by Doing from Your Browser Sidebar
Simply install the browser extension and click to launch GetVM directly from your sidebar.
Choose your OS, IDE, or app from our playground library and launch it instantly.
Practice within the VM while following tutorials or videos side-by-side. Save your work with Pro for easy continuity.