國立虎尾科技大學 |

Neural Approximations for Optimal Control and Decision

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Neural Approximations for Optimal Control and Decision/ by Riccardo Zoppoli, Marcello Sanguineti, Giorgio Gnecco, Thomas Parisini.
作者:	Zoppoli, Riccardo.
其他作者:	Sanguineti, Marcello.
面頁冊數:	XVIII, 517 p. 99 illus., 8 illus. in color.online resource. :
Contained By:	Springer Nature eBook
標題:	Control engineering. -
電子資源:	https://doi.org/10.1007/978-3-030-29693-3
ISBN:	9783030296933

Neural Approximations for Optimal Control and Decision
Zoppoli, Riccardo.

Neural Approximations for Optimal Control and Decision[electronic resource] /by Riccardo Zoppoli, Marcello Sanguineti, Giorgio Gnecco, Thomas Parisini. - 1st ed. 2020. - XVIII, 517 p. 99 illus., 8 illus. in color.online resource. - Communications and Control Engineering,0178-5354. - Communications and Control Engineering,.

Chapter 1. The Basic Inﬁnite-Dimensional or Functional Optimization Problem -- Chapter 2. From Functional Optimization to Nonlinear Programming by the Extended Ritz Method -- Chapter 3. Some Families of FSP Functions and Their Properties -- Chapter 4. Design of Mathematical Models by Learning from Data and FSP Functions -- Chapter 5. Numerical Methods for Integration and Search for Minima -- Chapter 6. Deterministic Optimal Control Over a Finite Horizon -- Chapter 7. Stochastic Optimal Control with Perfect State Information over a Finite Horizon -- Chapter 8. Stochastic Optimal Control with Imperfect State Information over a Finite Horizon -- Chapter 9. Team Optimal Control Problems -- Chapter 10. Optimal Control Problems over an Inﬁnite Horizon -- Index.

Neural Approximations for Optimal Control and Decision provides a comprehensive methodology for the approximate solution of functional optimization problems using neural networks and other nonlinear approximators where the use of traditional optimal control tools is prohibited by complicating factors like non-Gaussian noise, strong nonlinearities, large dimension of state and control vectors, etc. Features of the text include: • a general functional optimization framework; • thorough illustration of recent theoretical insights into the approximate solutions of complex functional optimization problems; • comparison of classical and neural-network based methods of approximate solution; • bounds to the errors of approximate solutions; • solution algorithms for optimal control and decision in deterministic or stochastic environments with perfect or imperfect state measurements over a finite or infinite time horizon and with one decision maker or several; • applications of current interest: routing in communications networks, traffic control, water resource management, etc.; and • numerous, numerically detailed examples. The authors’ diverse backgrounds in systems and control theory, approximation theory, machine learning, and operations research lend the book a range of expertise and subject matter appealing to academics and graduate students in any of those disciplines together with computer science and other areas of engineering.

ISBN: 9783030296933

Standard No.: 10.1007/978-3-030-29693-3doiSubjects--Topical Terms:

1249728
Control engineering.

LC Class. No.: TJ212-225

Dewey Class. No.: 629.8

Neural Approximations for Optimal Control and Decision
LDR:03698nam a22003975i 4500 001 1018485
003 DE-He213
005 20200704161512.0
007 cr nn 008mamaa
008 210318s2020 gw | s |||| 0|eng d
020 $a 9783030296933 $9 978-3-030-29693-3
024 7 $a 10.1007/978-3-030-29693-3 $2 doi
035 $a 978-3-030-29693-3
050 4 $a TJ212-225
072 7 $a TJFM $2 bicssc
072 7 $a TEC004000 $2 bisacsh
072 7 $a TJFM $2 thema
082 0 4 $a 629.8 $2 23
100 1 $a Zoppoli, Riccardo. $e author. $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1313490
245 1 0 $a Neural Approximations for Optimal Control and Decision $h [electronic resource] / $c by Riccardo Zoppoli, Marcello Sanguineti, Giorgio Gnecco, Thomas Parisini.
250 $a 1st ed. 2020.
264 1 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a XVIII, 517 p. 99 illus., 8 illus. in color. $b online resource.
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
347 $a text file $b PDF $2 rda
490 1 $a Communications and Control Engineering, $x 0178-5354
505 0 $a Chapter 1. The Basic Inﬁnite-Dimensional or Functional Optimization Problem -- Chapter 2. From Functional Optimization to Nonlinear Programming by the Extended Ritz Method -- Chapter 3. Some Families of FSP Functions and Their Properties -- Chapter 4. Design of Mathematical Models by Learning from Data and FSP Functions -- Chapter 5. Numerical Methods for Integration and Search for Minima -- Chapter 6. Deterministic Optimal Control Over a Finite Horizon -- Chapter 7. Stochastic Optimal Control with Perfect State Information over a Finite Horizon -- Chapter 8. Stochastic Optimal Control with Imperfect State Information over a Finite Horizon -- Chapter 9. Team Optimal Control Problems -- Chapter 10. Optimal Control Problems over an Inﬁnite Horizon -- Index.
520 $a Neural Approximations for Optimal Control and Decision provides a comprehensive methodology for the approximate solution of functional optimization problems using neural networks and other nonlinear approximators where the use of traditional optimal control tools is prohibited by complicating factors like non-Gaussian noise, strong nonlinearities, large dimension of state and control vectors, etc. Features of the text include: • a general functional optimization framework; • thorough illustration of recent theoretical insights into the approximate solutions of complex functional optimization problems; • comparison of classical and neural-network based methods of approximate solution; • bounds to the errors of approximate solutions; • solution algorithms for optimal control and decision in deterministic or stochastic environments with perfect or imperfect state measurements over a finite or infinite time horizon and with one decision maker or several; • applications of current interest: routing in communications networks, traffic control, water resource management, etc.; and • numerous, numerically detailed examples. The authors’ diverse backgrounds in systems and control theory, approximation theory, machine learning, and operations research lend the book a range of expertise and subject matter appealing to academics and graduate students in any of those disciplines together with computer science and other areas of engineering.
650 0 $a Control engineering. $3 1249728
650 0 $a System theory. $3 566168
650 0 $a Operations research. $3 573517
650 0 $a Decision making. $3 528319
650 0 $a Artificial intelligence. $3 559380
650 0 $a Mathematical optimization. $3 527675
650 1 4 $a Control and Systems Theory. $3 1211358
650 2 4 $a Systems Theory, Control. $3 669337
650 2 4 $a Operations Research/Decision Theory. $3 669176
650 2 4 $a Artificial Intelligence. $3 646849
650 2 4 $a Optimization. $3 669174
700 1 $a Sanguineti, Marcello. $e author. $1 https://orcid.org/0000-0003-0355-8483 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1313491
700 1 $a Gnecco, Giorgio. $e author. $1 https://orcid.org/0000-0002-5427-4328 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1313492
700 1 $a Parisini, Thomas. $e author. $1 https://orcid.org/0000-0001-5396-9665 $4 aut $4 http://id.loc.gov/vocabulary/relators/aut $3 1313493
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer Nature eBook
776 0 8 $i Printed edition: $z 9783030296919
776 0 8 $i Printed edition: $z 9783030296926
830 0 $a Communications and Control Engineering, $x 0178-5354 $3 1254247
856 4 0 $u https://doi.org/10.1007/978-3-030-29693-3
912 $a ZDB-2-INR
912 $a ZDB-2-SXIT
950 $a Intelligent Technologies and Robotics (SpringerNature-42732)
950 $a Intelligent Technologies and Robotics (R0) (SpringerNature-43728)