by Dimitri P. Bertsekas and John Tsitsiklis
ISBN: 1-886529-10-8
Publication: September 1996, 512 pages, hardcover
Price: $69.00
Contents, Preface, Ordering, Home
This is the first textbook that fully explains the neuro-dynamic programming/reinforcement learning methodology, which is a recent breakthrough in the practical application of neural networks and dynamic programming to complex problems of planning, optimal decision making, and intelligent control.
Neuro-dynamic programming uses neural network approximations to overcome the "curse of dimensionality" and the "curse of modeling" that have been the bottlenecks to the practical application of dynamic programming and stochastic control to complex problems. The methodology allows systems to learn about their behavior through simulation, and to improve their performance through iterative reinforcement.
This book provides the first systematic presentation of the science and the art behind this exciting and far-reaching methodology.
The book develops a comprehensive analysis of neuro-dynamic programming algorithms, and guides the reader to their successful application through case studies from complex problem areas.
"Neurodynamic Programming is a remarkable monograph that integrates a sweeping mathematical and computational landscape into a coherent body of rigorous knowledge. The topics are current, the writing is clear and to the point, the examples are comprehensive and the historical notes and comments are scholarly."
"In this monograph, Bertsekas and Tsitsiklis have performed a Herculean task that will be studied and appreciated by generations to come. I strongly recommend it to scientists and engineers eager to seriously understand the mathematics and computations behind modern behavioral machine learning."
Comments by Martin L. Puterman:"I believe that Neuro-Dynamic Programming by Bertsekas and Tsitsiklis will have a major impact on operations research theory and practice over the next decade. The methods it presents will produce solution of many large scale sequential optimization problems that up to now have proved intractable. The book systematically provides countless new ideas, concepts and problems, and will stimulate considerable future research in operations research and computer science on this exciting and important subject."
Among its special features, the book:
The authors are Professors of Electrical Engineering and Computer Science at the Massachusetts Institute of Technology, and members of the US National Academy of Engineering. They have been awarded several prestigious awards, including the INFORMS John von Neumann Theory Prize, for the contributions of the research monographs "Neuro-Dynamic Programming" and "Parallel and Distributed Computation".
