Cantitate/Preț
Produs
Total produse
Vezi coșul
Reinforcement Learning: Optimal Feedback Control with Industrial Applications de Jinna Li

Reinforcement Learning: Optimal Feedback Control with Industrial Applications: Advances in Industrial Control

Autor Jinna Li, Frank L. Lewis, Jialu Fan
en Limba Engleză Hardback – 25 iul 2023

În volumul Reinforcement Learning, autorii Jinna Li, Frank L. Lewis și Jialu Fan explorează convergența dintre controlul feedback optim și inovațiile tehnologice din sfera învățării prin recompensă (RL). Considerăm că această lucrare este esențială pentru inginerii care activează în automatizări, deoarece nu se limitează la mediile simulate, ci abordează direct complexitatea sistemelor neliniare și a celor în rețea (networked systems), unde dinamica este adesea necunoscută sau parțial observabilă. Notăm cu interes tranziția de la arhitecturile clasice de control la algoritmi avansați de tip data-driven, capabili să optimizeze eficiența învățării în sisteme multi-agent.

Structura cărții, publicată în seria Advances in Industrial Control, reflectă o progresie riguroasă. Primele capitole stabilesc fundamentul teoretic prin programare dinamică, fiind urmate de secțiuni tehnice dedicate controlului H-infinity și reglării output-ului. Abordarea diferă de Reinforcement Learning for Optimal Feedback Control de Rushikesh Kamalapurkar prin faptul că este mai puțin orientată spre identificarea modelelor în timp real și mai mult axată pe implementarea practică a algoritmilor de tip „Off-Policy Game RL” pentru industriile de proces. În timp ce Handbook of Reinforcement Learning and Control oferă o perspectivă enciclopedică, volumul de față este mai aplicat, oferind exemple numerice ilustrative pentru sincronizarea sistemelor multi-agent și optimizarea proceselor chimice sau miniere.

Fiecare capitol, de la designul observatorilor la Q-Learning-ul intercalat, este conceput pentru a oferi soluții la provocări industriale reale. Credem că echilibrul între analiza teoretică și studiile de caz din industria de putere sau prelucrare face din această ediție din 2023 un instrument de lucru indispensabil pentru cercetătorii care doresc să implementeze controlul adaptiv într-un cadru formal, dar pragmatic.

Citește tot Restrânge

Din seria Advances in Industrial Control

Preț: 86431 lei

Preț vechi: 105404 lei
-18%

Puncte Express: 1296

Carte disponibilă

Livrare economică 02-16 mai

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783031283932
ISBN-10: 3031283937
Pagini: 310
Ilustrații: XVI, 310 p. 114 illus., 110 illus. in color.
Dimensiuni: 155 x 235 mm
Greutate: 0.68 kg
Ediția:1st ed. 2023
Editura: Springer International Publishing
Colecția Springer
Seria Advances in Industrial Control

Locul publicării:Cham, Switzerland

De ce să citești această carte

Această lucrare se adresează specialiștilor în automatică și AI care caută să aplice învățarea prin recompensă în contexte industriale riguroase. Cititorul câștigă o înțelegere profundă a modului în care algoritmii RL pot gestiona sisteme cu parametri necunoscuți, oferind un avantaj competitiv în optimizarea proceselor complexe, de la rețele energetice la sisteme multi-agent, fără a sacrifica stabilitatea matematică a controlului feedback.

Despre autor

Autorii sunt cercetători de prestigiu în domeniul sistemelor de control. Frank L. Lewis este o figură proeminentă în ingineria sistemelor, fiind recunoscut pentru contribuțiile sale vaste în controlul feedback și sistemele inteligente. Alături de Jinna Li și Jialu Fan, acesta aduce o expertiză vastă în dezvoltarea algoritmilor de învățare pentru controlul robust și jocurile diferențiale. Activitatea lor colectivă, reflectată în numeroase publicații la Springer International Publishing, se concentrează pe aplicabilitatea practică a inteligenței artificiale în ingineria electrică și automatizarea proceselor industriale complexe.

Descriere scurtă

This book offers a thorough introduction to the basics and scientific and technological innovations involved in the modern study of reinforcement-learning-based feedback control. The authors address a wide variety of systems including work on nonlinear, networked, multi-agent and multi-player systems.
 
A concise description of classical reinforcement learning (RL), the basics of optimal control with dynamic programming and network control architectures, and a brief introduction to typical algorithms build the foundation for the remainder of the book. Extensive research on data-driven robust control for nonlinear systems with unknown dynamics and multi-player systems follows. Data-driven optimal control of networked single- and multi-player systems leads readers into the development of novel RL algorithms with increased learning efficiency. The book concludes with a treatment of how these RL algorithms can achieve optimal synchronization policies for multi-agentsystems with unknown model parameters and how game RL can solve problems of optimal operation in various process industries. Illustrative numerical examples and complex process control applications emphasize the realistic usefulness of the algorithms discussed.
 
The combination of practical algorithms, theoretical analysis and comprehensive examples presented in Reinforcement Learning will interest researchers and practitioners studying or using optimal and adaptive control, machine learning, artificial intelligence, and operations research, whether advancing the theory or applying it in mineral-process, chemical-process, power-supply or other industries.

Cuprins

1. Background on Reinforcement Learning and Optimal Control.- 2. H-infinity Control Using Reinforcement Learning.- 3. Robust Tracking Control and Output Regulation.- 4. Interleaved Robust Reinforcement Learning.- 5. Optimal Networked Controller and Observer Design.- 6. Interleaved Q-Learning.- 7. Off-Policy Game Reinforcement Learning.- 8. Game Reinforcement Learning for Process Industries.

Notă biografică

Professor Jinna Li received the M.S. degree and the Ph. D. degree from Northeastern University, Shenyang, China, 2006 and 2009, respectively. She is an associate professor at Shenyang University of Chemical Technology, Shenyang, China. From April 2009 to April 2011, she carried out postdoctoral research at the Lab of Industrial Control Networks and Systems, Shenyang Institute of Automation, Chinese Academy of Sciences. From June 2014 to June 2015, she was a Visiting Scholar granted by China Scholarship Council with Energy Research Institute, Nanyang Technological University, Singapore. From September 2015 to June 2016, she was a Domestic Young Core Visiting Scholar granted by Ministry of Education of China with State Key Lab of Synthetical Automation for Process Industries, Northeastern University. From Jan. 2017 to Jul. 2017, she was a Visiting Scholar with the School of Electrical and Electronic Engineering, the University of Manchester, UK. Her current research interests include neural networks, reinforcement learning, optimal operational control, distributed optimization control and data-based control. She has authored two P.R.China patents, more than 40 journal papers, more than 20 conference papers, one books. Dr. Li is a Senior Fellow of the Institute of Electrical and Electronic Engineers. She presided 3 projects from the National Natural Science Foundation of China and 5 projects from provincial funding in P. R. China.
Frank L. Lewis is a Distinguished Scholar Professor and Moncrief-O’Donnell Chair at University of Texas at Arlington’s Automation & Robotics Research Institute. He obtained his Bachelor’s Degree in Physics/EE and MSEE at Rice University, his MS in Aeronautical Engineering from Univ. W. Florida, and his Ph.D. at Ga. Tech. He received the Fulbright Research Award, the Outstanding Service Award from Dallas IEEE Section, and was selected as Engineer of the year by Ft. Worth IEEE Section. He is an elected Guest Consulting Professor at South China University of Technology and Shanghai Jiao Tong University. He is a Fellow of the IEEE, Fellow of IFAC, Fellow of the U.K. Institute of Measurement & Control, and a U.K. Chartered Engineer. His current research interests include distributed control on graphs, neural and fuzzy systems, and intelligent control.

Associate Professor Jialu Fan, graduated from Northeastern University with a bachelor's degree in automation in 2006; in 2011, she graduated from Zhejiang University with a Ph.D. in engineering; from 2009 to 2010, she was sponsored by the China Scholarship Council as a visiting researcher at Pennsylvania State University. Her research interests include networked operation control, industrial wireless networks and mobile social networks. She is co-author of Data Dissemination and Query in Mobile Social Networks (ISBN 978-1-4614-2253-2, Springer) and (at the invitation of Professor Pedro Albertos, it’s second author) of a Chinese translation of  Feedback and Control for Everyone (Original English ISBN 978-3-642-03445-9, Springer). She has published more than 30 academic papers in the field of network communication in various IEEE Journals and in conferences in the field of control. Associate Professor Fan has been responsible for two National Natural Science Foundation key projects along with a National Natural Science Foundation youth project and 3 provincial and ministerial-level projects. She particapted as a key member, in the National 973 Program, 863 Key Program and National Natural Science Foundation of China. She has served as a reviewer for top international SCI journals such as the IEEE Transactions on Automatic Control, IEEE Transactions on Control Systems Technology and IEEE Network Magazine. She served as Secretary-General of World Congress on Intelligent Control and Automation in 2014, as Branch Chair of the Asian Control Conference 2015, and on the program committees of editions of the Indian Control Conference, Globecom and SmartGridComm. He is now a member of the Youth Working Committee of the Chinese Society of Automation and a member of the International Association of Electrical and Electronics Engineers. She has won numerous honors as an outstanding educator, supervisor and mentor.

Caracteristici

Systematic, easy-to-follow introduction of novel ideas in data-driven optimal control Uses measured data in examples to show how methods really work Illustrates the practical application of novel algorithms in process-industrial systems