By Derong Liu, Qinglai Wei, Ding Wang, Xiong Yang, Hongliang Li
This publication covers the newest advancements in adaptive dynamic programming (ADP). The textual content starts with a radical historical past evaluate of ADP to ensure that readers are sufficiently conversant in the basics. within the middle of the ebook, the authors deal with first discrete- after which continuous-time platforms. insurance of discrete-time structures starts off with a extra common type of price generation to illustrate its convergence, optimality, and balance with whole and thorough theoretical research. A extra reasonable kind of price new release is studied the place price functionality approximations are assumed to have finite blunders. Adaptive Dynamic Programming additionally information one other street of the ADP process: coverage new release. either uncomplicated and generalized sorts of policy-iteration-based ADP are studied with entire and thorough theoretical research when it comes to convergence, optimality, balance, and blunder bounds. between continuous-time structures, the keep an eye on of affine and nonaffine nonlinear platforms is studied utilizing the ADP method that's then prolonged to different branches of keep an eye on idea together with decentralized keep an eye on, powerful and warranted rate keep an eye on, and online game concept. within the final a part of the booklet the real-world importance of ADP thought is gifted, concentrating on 3 software examples constructed from the authors’ work:
• renewable power scheduling for shrewdpermanent energy grids;• coal gasification tactics; and• water–gas shift reactions.
Researchers learning clever regulate tools and practitioners seeking to follow them within the chemical-process and power-supply industries will locate a lot to curiosity them during this thorough therapy of a sophisticated method of control.
Read or Download Adaptive Dynamic Programming with Applications in Optimal Control PDF
Similar robotics & automation books
For plenty of electronic structures, linearity is believed. The ebook then explains how a chic keep an eye on platforms thought might be utilized to layout and comprehend such structures. the mathematics comprises advanced research, on the point of Marsden's therapy, uncomplicated advanced research. so that you the right way to outline a move functionality matrix and locate its poles and zeros.
Simultaneous Localisation and Map (SLAM) construction algorithms, which depend upon random vectors to symbolize sensor measurements and have maps are recognized to be tremendous fragile within the presence of function detection and knowledge organization uncertainty. consequently new recommendations for independent map representations are given during this publication, in line with random finite units (RFSs).
This e-book demonstrates using the optimization ideas which are turning into necessary to meet the expanding stringency and diversity of necessities for automobile platforms. It exhibits the reader the best way to stream clear of past ways, in keeping with a point of heuristics, to using a growing number of universal systematic equipment.
This publication covers the newest advancements in adaptive dynamic programming (ADP). The textual content starts with an intensive historical past evaluation of ADP with the intention that readers are sufficiently acquainted with the basics. within the middle of the booklet, the authors deal with first discrete- after which continuous-time platforms.
- Regelungstechnik I: Klassische Verfahren zur Analyse und Synthese linearer kontinuierlicher Regelsysteme, Fuzzy-Regelsysteme
- Regelungstechnik 1: Systemtheoretische Grundlagen, Analyse und Entwurf einschleifiger Regelungen
- The Control Handbook, Second Edition: Control System Fundamentals, Second Edition (Electrical Engineering Handbook)
- Parallel Robots
- Information Path Functional and Informational Macrodynamics
- Flugmechanik der Hubschrauber: Technologie, das flugdynamische System Hubschrauber, Flugstabilitäten, Steuerbarkeit
Extra resources for Adaptive Dynamic Programming with Applications in Optimal Control
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. This gives the same idea as in the forward-in-time approach shown in Fig. 2, where the target is Uk + γ Jˆk+1 . The only difference is the definition of reward function.
Lendaris GG, Paintz C (1997) Training strategies for critic and action neural networks in dual heuristic programming method. In: Proceedings of the IEEE international conference on neural networks, pp 712–717 References 29 40. Lewis FL, Liu D (2012) Reinforcement learning and approximate dynamic programming for feedback control. Wiley, Hoboken, NJ 41. Lewis FL, Syrmos VL (1995) Optimal control. Wiley, New York 42. Lewis FL, Vrabie D (2009) Reinforcement learning and adaptive dynamic programming for feedback control.
Balakrishnan SN, Biega V (1996) Adaptive-critic-based neural networks for aircraft optimal control. AIAA J Guid Control Dyn 19:893–898 7. Barto AG (1992) Reinforcement learning and adaptive critic methods. In: White DA, Sofge DA (eds) Handbook of intelligent control: neural, fuzzy, and adaptive approaches (chapter 12). Van Nostrand Reinhold, New York 8. Baudis P, Gailly JL (2012) PACHI: state of the art open source Go program. In: Advances in computer games (Lecture notes in computer science), vol 7168.