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...

Full description

Saved in:
Bibliographic Details
Main Author: Bellemare, Marc G. (auth)
Other Authors: Dabney, Will (auth), Rowland, Mark (auth)
Format: Electronic Book Chapter
Language:English
Published: Cambridge The MIT Press 2023
Series:Adaptive Computation and Machine Learning series
Subjects:
Online Access:DOAB: download the publication
DOAB: description of the publication
Tags: Add Tag
No Tags, Be the first to tag this record!

MARC

LEADER 00000naaaa2200000uu 4500
001 doab_20_500_12854_111581
005 20230731
003 oapen
006 m o d
007 cr|mn|---annan
008 20230731s2023 xx |||||o ||| 0|eng d
020 |a mitpress/14207.001.0001 
020 |a 9780262374026 
020 |a 9780262048019 
040 |a oapen  |c oapen 
024 7 |a 10.7551/mitpress/14207.001.0001  |c doi 
041 0 |a eng 
042 |a dc 
072 7 |a PBT  |2 bicssc 
072 7 |a UYQM  |2 bicssc 
100 1 |a Bellemare, Marc G.  |4 auth 
700 1 |a Dabney, Will  |4 auth 
700 1 |a Rowland, Mark  |4 auth 
245 1 0 |a Distributional Reinforcement Learning 
260 |a Cambridge  |b The MIT Press  |c 2023 
300 |a 1 electronic resource (384 p.) 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
490 1 |a Adaptive Computation and Machine Learning series 
506 0 |a Open Access  |2 star  |f Unrestricted online access 
520 |a 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. 
540 |a Creative Commons  |f https://creativecommons.org/licenses/BY-NC-ND/4.0/  |2 cc  |4 https://creativecommons.org/licenses/BY-NC-ND/4.0/ 
546 |a English 
650 7 |a Probability & statistics  |2 bicssc 
650 7 |a Machine learning  |2 bicssc 
653 |a Computer Science/Machine Learning & Neural Networks 
856 4 0 |a www.oapen.org  |u https://doi.org/10.7551/mitpress/14207.001.0001  |7 0  |z DOAB: download the publication 
856 4 0 |a www.oapen.org  |u https://directory.doabooks.org/handle/20.500.12854/111581  |7 0  |z DOAB: description of the publication