A high school student can create deep Q-learning code to control her robot, without any understanding of the meaning of 'deep' or 'Q', or why the code sometimes fails. This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra. A unique focus is algorithm design to obtain the fastest possible speed of convergence for learning algorithms, along with insight into why reinforcement learning sometimes fails. Advanced stochastic process theory is avoided at the start by substituting random exploration with more intuitive deterministic probing for learning. Once these ideas are understood, it is not difficult to master techniques rooted in stochastic control. These topics are covered in the second part of the book, starting with Markov chain theory and ending with a fresh look at actor-critic methods for reinforcement learning.
"Sinopsis" puede pertenecer a otra edición de este libro.
Sean Meyn is a professor and holds the Robert C. Pittman Eminent Scholar Chair in the Department of Electrical and Computer Engineering, University of Florida. He is well known for his research on stochastic processes and their applications. His award-winning monograph Markov Chains and Stochastic Stability with R. L. Tweedie is now a standard reference. In 2015 he and Prof. Ana Busic received a Google Research Award recognizing research on renewable energy integration. He is an IEEE Fellow and IEEE Control Systems Society distinguished lecturer on topics related to both reinforcement learning and energy systems.
"Sobre este título" puede pertenecer a otra edición de este libro.
GRATIS gastos de envío en Estados Unidos de America
Destinos, gastos y plazos de envíoEUR 7,67 gastos de envío en Estados Unidos de America
Destinos, gastos y plazos de envíoLibrería: Best Price, Torrance, CA, Estados Unidos de America
Condición: New. SUPER FAST SHIPPING. Nº de ref. del artículo: 9781316511961
Cantidad disponible: 2 disponibles
Librería: GreatBookPrices, Columbia, MD, Estados Unidos de America
Condición: New. Nº de ref. del artículo: 44152455-n
Cantidad disponible: 1 disponibles
Librería: World of Books (was SecondSale), Montgomery, IL, Estados Unidos de America
Condición: Very Good. Item in very good condition! Textbooks may not include supplemental items i.e. CDs, access codes etc. Nº de ref. del artículo: 00089626898
Cantidad disponible: 1 disponibles
Librería: Lucky's Textbooks, Dallas, TX, Estados Unidos de America
Condición: New. Nº de ref. del artículo: ABLIING23Mar2411530051093
Cantidad disponible: Más de 20 disponibles
Librería: California Books, Miami, FL, Estados Unidos de America
Condición: New. Nº de ref. del artículo: I-9781316511961
Cantidad disponible: Más de 20 disponibles
Librería: PBShop.store UK, Fairford, GLOS, Reino Unido
HRD. Condición: New. New Book. Shipped from UK. Established seller since 2000. Nº de ref. del artículo: GB-9781316511961
Cantidad disponible: 3 disponibles
Librería: GreatBookPrices, Columbia, MD, Estados Unidos de America
Condición: As New. Unread book in perfect condition. Nº de ref. del artículo: 44152455
Cantidad disponible: 1 disponibles
Librería: Books Puddle, New York, NY, Estados Unidos de America
Condición: New. New edition NO-PA16APR2015-KAP. Nº de ref. del artículo: 26390160860
Cantidad disponible: 1 disponibles
Librería: Majestic Books, Hounslow, Reino Unido
Condición: New. Nº de ref. del artículo: 389471747
Cantidad disponible: 1 disponibles
Librería: Grand Eagle Retail, Mason, OH, Estados Unidos de America
Hardcover. Condición: new. Hardcover. A high school student can create deep Q-learning code to control her robot, without any understanding of the meaning of 'deep' or 'Q', or why the code sometimes fails. This book is designed to explain the science behind reinforcement learning and optimal control in a way that is accessible to students with a background in calculus and matrix algebra. A unique focus is algorithm design to obtain the fastest possible speed of convergence for learning algorithms, along with insight into why reinforcement learning sometimes fails. Advanced stochastic process theory is avoided at the start by substituting random exploration with more intuitive deterministic probing for learning. Once these ideas are understood, it is not difficult to master techniques rooted in stochastic control. These topics are covered in the second part of the book, starting with Markov chain theory and ending with a fresh look at actor-critic methods for reinforcement learning. The book is written for newcomers to reinforcement learning who wish to write code for various applications, from robotics to power systems to supply chains. It also contains advanced material designed to prepare graduate students and professionals for both research and application of reinforcement learning and optimal control techniques. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Nº de ref. del artículo: 9781316511961
Cantidad disponible: 1 disponibles