Navigation überspringen
Universitätsbibliothek Heidelberg
Standort: ---
Exemplare: ---

+ Andere Auflagen/Ausgaben
 Online-Ressource
Verfasst von:Bellemare, Marc G. [VerfasserIn]   i
 Dabney, Will [VerfasserIn]   i
 Rowland, Mark [VerfasserIn]   i
Titel:Distributional Reinforcement Learning
Verlagsort:Cambridge
Verlag:The MIT Press
Jahr:2023
Umfang:1 Online-Ressource (384 p.)
Gesamttitel/Reihe:Adaptive Computation and Machine Learning series
Schrift/Sprache:English
ISBN:978-0-262-37402-6
 978-0-262-04801-9
Abstract:The first comprehensive guide to distributional reinforcement learning, providing a new mathematical formalism for thinking about decisions from a probabilistic perspective.Distributional reinforcement learning is a new mathematical formalism for thinking about decisions. Going beyond the common approach to reinforcement learning and expected values, it focuses on the total reward or return obtained as a consequence of an agent's choices—specifically, how this return behaves from a probabilistic perspective. In this first comprehensive guide to distributional reinforcement learning, Marc G. Bellemare, Will Dabney, and Mark Rowland, who spearheaded development of the field, present its key concepts and review some of its many applications. They demonstrate its power to account for many complex, interesting phenomena that arise from interactions with one's environment.The authors present core ideas from classical reinforcement learning to contextualize distributional topics and include mathematical proofs pertaining to major results discussed in the text. They guide the reader through a series of algorithmic and mathematical developments that, in turn, characterize, compute, estimate, and make decisions on the basis of the random return. Practitioners in disciplines as diverse as finance (risk management), computational neuroscience, computational psychiatry, psychology, macroeconomics, and robotics are already using distributional reinforcement learning, paving the way for its expanding applications in mathematical finance, engineering, and the life sciences. More than a mathematical approach, distributional reinforcement learning represents a new perspective on how intelligent agents make predictions and decisions
 "Distributional reinforcement learning provides a mathematical theory to describe the random outcomes caused by an agent's decisions"--
URL:kostenfrei: Verlag: https://directory.doabooks.org/handle/20.500.12854/111581
 20.500.12854/111581
Schlagwörter:(s)Bestärkendes Lernen <Künstliche Intelligenz>   i / (s)Agent <Informatik>   i / (s)Entscheidungsfunktion   i
Datenträger:Online-Ressource
Sprache:und
Bibliogr. Hinweis:Erscheint auch als : Druck-Ausgabe: Nguyen, Quan: Bayesian Optimization in Action. - Shelter Island : Manning, 2023. - xxvi, 396 Seiten
Sach-SW:Probability & statistics
 Machine learning
K10plus-PPN:1869162110
 
 
Lokale URL UB: Zum Volltext

Permanenter Link auf diesen Titel (bookmarkfähig):  https://katalog.ub.uni-heidelberg.de/titel/69137686   QR-Code

zum Seitenanfang