東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems./
Author:	Zeng, Kevin.
Description:	1 online resource (235 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
Contained By:	Dissertations Abstracts International84-11B.
Subject:	Chemical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30490278click for full text (PQDT)
ISBN:	9798379507732

Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems.
Zeng, Kevin.

Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems. - 1 online resource (235 pages)

Source: Dissertations Abstracts International, Volume: 84-11, Section: B.

Thesis (Ph.D.)--The University of Wisconsin - Madison, 2023.

Includes bibliographical references

Many ubiquitous phenomena in nature and engineering, such as turbulent flows, global weather patterns, and reaction-diffusion systems, can be described by dissipative infinite dimensional partial differential equations. Despite their prevalence, these systems often remain the source of engineering challenges when it comes to modeling and control. Specifically, generalizable and automated frameworks for reduced-order modeling and control remain an obstacle due to a number of systemic challenges such as complex spatiotemporal chaotic dynamics, high-dimensionality, and costly data generation. While many deep learning frameworks have experienced dramatic success in their fields of origin, their direct application towards our target systems can often be unsatisfactory or even intractable without innovation. Motivated by this disconnect, the main objective in this thesis is therefore to develop data-driven frameworks that combine concepts from dynamical systems theory, such as symmetries and manifolds, with deep learning, such as deep reinforcement learning (RL) and representation learning, to efficiently and automatically find control strategies and low-dimensional representations for complex dynamical systems.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798379507732Subjects--Topical Terms:

560457
Chemical engineering.
Subjects--Index Terms:

ChaosIndex Terms--Genre/Form:

542853
Electronic books.

Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems.
LDR:02657nmm a2200409K 4500 001 2360770
005 20231015184519.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798379507732
035 $a (MiAaPQ)AAI30490278
035 $a AAI30490278
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Zeng, Kevin. $3 3701402
245 1 0 $a Deep Reinforcement Learning and Representation Learning for Chaotic Dynamical Systems.
264 0 $c 2023
300 $a 1 online resource (235 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 84-11, Section: B.
500 $a Advisor: Graham, Michael D.
502 $a Thesis (Ph.D.)--The University of Wisconsin - Madison, 2023.
504 $a Includes bibliographical references
520 $a Many ubiquitous phenomena in nature and engineering, such as turbulent flows, global weather patterns, and reaction-diffusion systems, can be described by dissipative infinite dimensional partial differential equations. Despite their prevalence, these systems often remain the source of engineering challenges when it comes to modeling and control. Specifically, generalizable and automated frameworks for reduced-order modeling and control remain an obstacle due to a number of systemic challenges such as complex spatiotemporal chaotic dynamics, high-dimensionality, and costly data generation. While many deep learning frameworks have experienced dramatic success in their fields of origin, their direct application towards our target systems can often be unsatisfactory or even intractable without innovation. Motivated by this disconnect, the main objective in this thesis is therefore to develop data-driven frameworks that combine concepts from dynamical systems theory, such as symmetries and manifolds, with deep learning, such as deep reinforcement learning (RL) and representation learning, to efficiently and automatically find control strategies and low-dimensional representations for complex dynamical systems.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Chemical engineering. $3 560457
650 4 $a Fluid mechanics. $3 528155
653 $a Chaos
653 $a Data representations
653 $a Deep learning
653 $a Dynamical systems
653 $a Machine learning
653 $a Reinforcement learning
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0542
690 $a 0204
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a The University of Wisconsin - Madison. $b Chemical Engineering. $3 2094015
773 0 $t Dissertations Abstracts International $g 84-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30490278 $z click for full text (PQDT)