Neuro dynamic programming
Material type: BookPublication details: Belmont, Mass : Athena Scientific, 1996.Description: 491 p.; ill.; 24 cmISBN:- 9781886529106
- 519.703 BER
Item type | Current library | Call number | Status | Date due | Barcode |
---|---|---|---|---|---|
Books | IIT Gandhinagar | 519.703 BER (Browse shelf(Opens below)) | Available | 024260 |
Neuro-dynamic programming, also known as reinforcement learning, is a recent methodology that can be used to solve very large and complex stochastic decision and control problems. It combines simulation, learning, neural networks or other approximation architectures, and the central ideas in dynamic programming. This book provides the first systematic presentation of the science and the art behind this promising methodology. It presents and unifies a large number of NDP methods, including several that are new; provides a rigorous development of the mathematical principles behind NDP; illustrates through case studies the practical application of NDP to complex problems and includes extensive background on dynamic programming and neural network training.
There are no comments on this title.