Distributional Reinforcement Learning

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 app...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bellemare, Marc G., Dabney, Will, Rowland, Mark
Format: Online
Sprache:Englisch
Veröffentlicht: The MIT Press 2023
Schlagworte:
Online-Zugang:ONIX_20230731_9780262374026_15
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
_version_ 1869526191409463296
author Bellemare, Marc G.
Dabney, Will
Rowland, Mark
author_browse Bellemare, Marc G.
Dabney, Will
Rowland, Mark
author_facet Bellemare, Marc G.
Dabney, Will
Rowland, Mark
author_sort Bellemare, Marc G.
collection Directory of Open Access Books
description 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.
format Online
id doab-20.500.12854ir-111581
institution Directory of Open Access Books
language eng
publishDate 2023
publishDateRange 2023
publishDateSort 2023
publisher The MIT Press
publisherStr The MIT Press
record_format ojs
spelling doab-20.500.12854ir-1115812024-04-04T14:41:15Z Distributional Reinforcement Learning Bellemare, Marc G. Dabney, Will Rowland, Mark Computer Science/Machine Learning & Neural Networks thema EDItEUR::P Mathematics and Science::PB Mathematics::PBT Probability and statistics thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning 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. 2023-07-31T10:53:52Z 2023-07-31T10:53:52Z 2023 book ONIX_20230731_9780262374026_15 9780262374026 9780262048019 https://directory.doabooks.org/handle/20.500.12854/111581 eng Adaptive Computation and Machine Learning series image/jpeg n/a https://doi.org/10.7551/mitpress/14207.001.0001 The MIT Press The MIT Press 10.7551/mitpress/14207.001.0001 10.7551/mitpress/14207.001.0001 ae0cf962-f685-4933-93d1-916defa5123d 9780262374026 9780262048019 The MIT Press 384 Cambridge open access
spellingShingle Computer Science/Machine Learning & Neural Networks
thema EDItEUR::P Mathematics and Science::PB Mathematics::PBT Probability and statistics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
Bellemare, Marc G.
Dabney, Will
Rowland, Mark
Distributional Reinforcement Learning
title Distributional Reinforcement Learning
title_full Distributional Reinforcement Learning
title_fullStr Distributional Reinforcement Learning
title_full_unstemmed Distributional Reinforcement Learning
title_short Distributional Reinforcement Learning
title_sort distributional reinforcement learning
topic Computer Science/Machine Learning & Neural Networks
thema EDItEUR::P Mathematics and Science::PB Mathematics::PBT Probability and statistics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
topic_facet Computer Science/Machine Learning & Neural Networks
thema EDItEUR::P Mathematics and Science::PB Mathematics::PBT Probability and statistics
thema EDItEUR::U Computing and Information Technology::UY Computer science::UYQ Artificial intelligence::UYQM Machine learning
url ONIX_20230731_9780262374026_15
work_keys_str_mv AT bellemaremarcg distributionalreinforcementlearning
AT dabneywill distributionalreinforcementlearning
AT rowlandmark distributionalreinforcementlearning