Reinforcement learning and dynamic programming using function approximators

Reinforcement learning and dynamic programming are key research areas in machine learning and artificial intelligence. This monograph describes algorithms from each of the three major classes of these techniques: value iteration, policy iteration, and direct policy search. Using illustrative examples, the textdiscusses the performance of these algorithms in a variety of applications, starting with simple examples such as servo-system control and then continuing on to more challenging problems such as robotic manipulator stabilization and bicycle balancing. The book concludes with the highly challenging problem of optimizing human immunodeficiency virus treatment.

• ISBN: 978-1-4398-2108-4
• Editorial: CRC Press
• Encuadernacion: Cartoné
• Páginas: 288
• Fecha Publicación: 26/04/2010
• Nº Volúmenes: 1
• Idioma: Inglés