0 ratings
Reinforcement Learning and Optimal Control
Vare #: 17157855

Reinforcement Learning and Optimal Control

Vare #: 17157855

DKK 852

Prisdetaljer

Eksklusive forsendelses- og toldgebyrer ( Forsendelses- og toldgebyrer beregnes ved checkout )

*Alle varer importeres fra US

På lager
US Importeret fra USA butik

QTY:

Bestil nu og få den omkring Fredag, December 04
Vores bedste logistikpartnere
  • fedex
  • dhl
Vis mere
U-Pleje garanti:
Ingen
Vælg en plan
buy now pay later

Køb nu, betal senere

fast shipping

Hurtig
levering

free return

Gratis
returnering*

Sikker emballering

Sikker emballering

100 % originale produkter'

100 % originale produkter'

pci-dss

PCI DSS Compliance

iso certified

ISO 27001 Certified


paypal payment
visa payment
mastercard payment
klarna payment
Note: Step Down Voltage Transformer required for using electronics products of US store (110 V-120 V). Recommended power converters Køb nu.

Hvad der skiller sig ud

Comprehensive Framework
Offers an integrated approach combining reinforcement learning with optimal control, addressing both theoretical concepts and practical applications for enhanced understanding and implementation in various contexts.
Real-World Applications
Equips readers with the necessary tools and methodologies to apply reinforcement learning techniques in real-world scenarios, ensuring relevance and usability in contemporary automated systems.
Expert Contributions
Authored by leading experts, this book provides authoritative insights and cutting-edge research, ensuring high-quality content that meets the needs of both academics and practitioners in the field.

Produktdetaljer

Get the best deals on Reinforcement Learning and Optimal Control First Edition at Ubuy. Shop now for a wide selection and great prices on Danmark. Fast and reliable shipping.
  • This book considers large and challenging multistage decision problems, which can be solved in principle by dynamic programming, but their exact solution is computationally intractable. It can be used as a textbook or for self-study in conjunction with instructional videos and slides, and other supporting material, which are available from the author's website. The book discusses solution methods that rely on approximations to produce suboptimal policies with adequate performance. These methods are known by several essentially equivalent names: reinforcement learning, approximate dynamic programming, and neuro-dynamic programming. They underlie, among others, the recent impressive successes of self-learning in the context of games such as chess and Go. One of the aims of the book is to explore the common boundary between artificial intelligence and optimal control, and to form a bridge that is accessible by workers with background in either field. Another aim is to organize coherently the broad mosaic of methods that have proved successful in practice while having a solid theoretical and/or logical foundation. This may help researchers and practitioners to find their way through the maze of competing ideas that constitute the current state of the art. The mathematical style of this book is somewhat different than other books by the same author. While we provide a rigorous, albeit short, mathematical account of the theory of finite and infinite horizon dynamic programming, and some fundamental approximation methods, we rely more on intuitive explanations and less on proof-based insights. We also illustrate the methodology with many example algorithms and applications.
Publisher Athena Scientific
Publication date July 15, 2019
Edition First Edition
Language English
Print length 388 pages
ISBN-10 1886529396
ISBN-13 978-1886529397
Item Weight 1.48 pounds (670 grams)
Dimensions 10 x 8 x 1.5 inches (25.4 x 20.3 x 3.8 cm)

Hvem bør købe?

Suitable For
  • Academic Researchers

    Ideal for researchers focusing on reinforcement learning and control theories to advance their studies and projects.

  • Graduate Students

    Beneficial for graduate students in computer science or engineering seeking to deepen their understanding of optimal control.

  • Industry Professionals

    Useful for professionals in AI or robotics looking to implement reinforcement learning for practical applications.

Not Suitable For
  • Casual Learners

    Not suitable for those seeking basic introductions or quick tutorials on reinforcement learning fundamentals.

Produktbeskrivelse

3-6 hverdage Delivery in Danmark

Shop the original Reinforcement Learning and Optimal Control from international stores and get express delivery to Copenhagen, Aarhus, Odense, and other cities across Danmark.

Har du spørgsmål? Chat med os

Kundespørgsmål og svar

  • spørgsmål: Hvordan shopper man Reinforcement Learning and Optimal Control online fra Ubuy?

    svar: Det er nemt at shoppe Reinforcement Learning and Optimal Control online fra Ubuy.. Du skal bare søge efter produktet, vælge din forsendelsesmetode, mens du tjekker ud og få det leveret til dit sted.
  • spørgsmål: Er Reinforcement Learning and Optimal Control tilgængelig til at handle online i Denmark?

    svar: Ja, hos Ubuy Denmark er dette produkt tilgængeligt, så du kan handle til en rimelig pris.. Reinforcement Learning and Optimal Control er ikke tilgængelig lokalt, men du kan stole på os med vores ekspresforsendelsestjenester.
  • spørgsmål: Hvor lang tid tager det at få produktet efter at have afgivet ordren?

    svar: Leveringstiden for dit bestilte produkt varierer alt efter, hvad du har bestilt, og den forsendelsesmetode, du har valgt.. Den estimerede leveringstid er nævnt under købsprocessen, så vær ubekymret, mens du handler.

Intelligence & Semantics Editorial Review

The Reinforcement Learning and Optimal Control First Edition by Bertsekas is praised for its technical expertise and mastery of exposition. The book offers clear explanations of the key ideas behind RL and optimal control and the differences between machine learning and traditional adaptive control approaches. The algorithms are thoroughly explained and made transparent. It is recommended for readers with a basic background in dynamic programming or control theory. The book is regarded as a must-read for anyone who wants to understand RL. The author uses a broad range of examples to guide readers starting from exact DP for finite-horizon problems. The book provides an understanding of RL for finite-horizon problems and DP and RL theory for infinite-horizon problems. The author also presents the aggregation method and its special characteristics. The book is good at explaining the theory of finite-state and finite-action problems in a self-contained and rigorous manner. The author reminds readers throughout the book that the potential challenges lie in the implementation of theoretical techniques.

Kundeanmeldelser & vurderinger

4.4
45 kundebedømmelser
  • 5 stjerne
    74%
  • 4 stjerne
    11%
  • 3 stjerne
    6%
  • 2 stjerne
    3%
  • 1 stjerne
    6%

Anmeld dette produkt

Del dine tanker med andre kunder

Fordele

  • Technical expertise and mastery of exposition.
  • Clear explanations of key ideas behind RL and optimal control.
  • Thoroughly explained algorithms.
  • Wide range of examples to guide readers.
  • Provides an understanding of RL for finite-horizon problems and DP and RL theory for infinite-horizon problems.
  • Explains the aggregation method and its special characteristics.
  • Self-contained and rigorous.

Platformstillid & Køberens Tillid

trustpilot logo
4.2/5 9971 reviews
Læs anmeldelser
MB
Mona
Verificeret køber

“Everything was efficient and fast. ”

05 November 2026 · via Trustpilot
MT
Musik
Verificeret køber

“The prices—including shipping costs and customs duties—are clear from the very beginning, with no hidden fees. I highly recommend using their services. My experience with the "Ubuy" website was excellent. I purchased a PRS USA Swamp Ash Special guitar, and it arrived in just 11 days. The shipping service was fantastic, and the product arrived in perfect condition. What I particularly appreciated about the site is that the prices—including shipping costs and customs duties—are clear from the very beginning, with no hidden fees. I highly recommend using their services.”

05 November 2026 · via Trustpilot
WF
William
Verificeret køber

“I can't fault this purchase. Had a scarce part i needed, cheaper than i could source it in the UK, ordered and was followed up with great communication and speedy delivery of a very well packaged part.”

06 November 2026 · via Trustpilot
Sv
Andrew
Verificeret køber

“Fast delivery, good and secure packaging, everything was fine and with no problems.”

06 November, 2026 · via Trustpilot
SM
Stephen
Verificeret køber

“I am very happy with my insoles purchase, they make my work boots very comfortable and soft to walk on and even mitigate the vibration from driving the truck all day. I would highly recommend this company for online purchases, reliability of product delivery and value for money.”

07 November 2026 · via Trustpilot

HVORFOR HANDLE HOS OS

Sikker betaling Global levering Nem returnering Originale produkter

Produktets prishistorik

Vigtig information

  • Begrænsninger: For produkter, der forsendes internationalt, bemærk venligst, at eventuel producentgaranti muligvis ikke er gyldig; producentens serviceordninger er muligvis ikke tilgængelige; produktmanualer, instruktioner og sikkerhedsadvarsler er muligvis ikke på destinationslandets sprog; produkterne (og det medfølgende materiale) er muligvis ikke designet i overensstemmelse med destinationslandets standarder, specifikationer og mærkningskrav; og produkterne opfylder muligvis ikke destinationslandets krav til spænding og andre elektriske standarder (hvilket kan kræve brug af en adapter eller transformer, hvis relevant). Modtageren er ansvarlig for at sikre, at produktet lovligt kan importeres til destinationslandet. Ved bestilling hos Ubuy eller dets datterselskaber er modtageren importøren og skal overholde alle love og regler i destinationslandet.
  • Det er ikke alle de produkter som vises på Ubuy som er til salg, idet Ubuy er en global søgemaskine. Produkterne er underlagt eksport-/handelsregler.