Adaptive Dynamic Programming with Applications in Optimal - download pdf or read online

By Derong Liu, Qinglai Wei, Ding Wang, Xiong Yang, Hongliang Li

ISBN-10: 331950813X

ISBN-13: 9783319508139

ISBN-10: 3319508156

ISBN-13: 9783319508153

This ebook covers the newest advancements in adaptive dynamic programming (ADP). The textual content starts with an intensive heritage assessment of ADP to ensure that readers are sufficiently conversant in the basics. within the middle of the e-book, the authors handle first discrete- after which continuous-time platforms. insurance of discrete-time platforms begins with a extra normal kind of price generation to illustrate its convergence, optimality, and balance with entire and thorough theoretical research. A extra practical kind of worth new release is studied the place worth functionality approximations are assumed to have finite error. Adaptive Dynamic Programming additionally info one other road of the ADP strategy: coverage generation. either uncomplicated and generalized types of policy-iteration-based ADP are studied with entire and thorough theoretical research by way of convergence, optimality, balance, and blunder bounds. between continuous-time platforms, the keep an eye on of affine and nonaffine nonlinear platforms is studied utilizing the ADP process that's then prolonged to different branches of regulate concept together with decentralized keep an eye on, powerful and assured expense keep watch over, and video game thought. within the final a part of the e-book the real-world importance of ADP idea is gifted, targeting 3 software examples constructed from the authors’ work:

• renewable power scheduling for clever strength grids;• coal gasification procedures; and• water–gas shift reactions.
Researchers learning clever keep an eye on equipment and practitioners seeking to observe them within the chemical-process and power-supply industries will locate a lot to curiosity them during this thorough therapy of a complicated method of control.

Show description

Read or Download Adaptive Dynamic Programming with Applications in Optimal Control PDF

Similar robotics & automation books

Air Logic Control for Automated Systems - download pdf or read online

As commercial strategies develop into increasingly more automatic, Air good judgment regulate (ALC) turns into more and more vital. because the use of ALC turns into extra frequent, the necessity for designers, engineers, and technicians with a operating wisdom of ALC expertise grows considerably. Air common sense regulate for computerized platforms presents the ability for an individual concerned with regulate structures to procure the information and abilities they should enforce and retain ALC for automatic production.

Complexity of Robot Motion Planning by John F. Canny PDF

The Complexity of robotic movement making plans makes unique contributions either to robotics and to the research of algorithms. during this groundbreaking monograph John Canny resolves long-standing difficulties about the complexity of movement making plans and, for the crucial challenge of discovering a collision loose course for a jointed robotic within the presence of stumbling blocks, obtains exponential speedups over latest algorithms by way of making use of high-powered new mathematical innovations.

Derong Liu, Qinglai Wei, Ding Wang, Xiong Yang, Hongliang Li's Adaptive Dynamic Programming with Applications in Optimal PDF

This e-book covers the newest advancements in adaptive dynamic programming (ADP). The textual content starts off with a radical historical past overview of ADP with the intention that readers are sufficiently accustomed to the basics. within the middle of the publication, the authors deal with first discrete- after which continuous-time structures.

Additional resources for Adaptive Dynamic Programming with Applications in Optimal Control

Example text

With the current trends in deep learning, big data, artificial intelligence, as well as cyber-physical systems and Internet of things, we believe that ADP will have a bright future. There are still many pending issues to be solved, and most of them are related to obtaining good approximations to solutions of dynamic programming with less computation. Deep reinforcement learning is able to output control signal directly based on input images, which incorporates both the advantages of the perception of deep learning and the decision-making of reinforcement learning.

Buro M (1998) From simple features to sophisticated evaluation functions. In: Proceedings of the international conference on computers and games (Lecture notes in computer science), vol 1558. pp 126–145 14. Busoniu L, Babuska R, De Schutter B, Ernst D (2010) Reinforcement learning and dynamic programming using function approximators. CRC Press, Boca Raton, FL 28 1 Overview of Adaptive Dynamic Programming 15. Cai X, Wunsch DC (2001) A parallel computer-Go player, using HDP method. In: Proceedings of the international joint conference on neural networks, pp 2373–2375 16.

6) as the output of the critic network to be trained and choose Uk + γ Jˆk+1 as the training target. Note that Jˆk and Jˆk+1 are obtained using state variables at different time instances. 3 shows the diagram of backward-in-time approach. 6) as the output of the critic network to be trained and choose (Jˆk − Uk )/γ as the training target. 7). In Figs. 3, xˆ k+1 is the output from the model network. 15), we can see that the learning objective is to minimize |rt+1 + γ V (st+1 ) − V (st )| by using rt+1 + γ V (st+1 ) as the learning target.

Download PDF sample

Adaptive Dynamic Programming with Applications in Optimal Control by Derong Liu, Qinglai Wei, Ding Wang, Xiong Yang, Hongliang Li


by David
4.1

Rated 4.62 of 5 – based on 25 votes