Пожалуйста, войдите в систему, чтобы принять участие в дискуссии (добавить собственные рецензию, или комментарий)
Цитировать эту публикацию
%0 Conference Paper
%1 conf/icic/ParkKMNH23
%A Park, Bumgeun
%A Kim, Taeyoung
%A Moon, Woohyeon
%A Nengroo, Sarvar Hussain
%A Har, Dongsoo
%B ICIC (5)
%D 2023
%E Huang, De-Shuang
%E Premaratne, Prashan
%E Jin, Baohua
%E Qu, Boyang
%E Jo, Kang-Hyun
%E Hussain, Abir
%I Springer
%K dblp
%P 600-613
%T Off-Policy Reinforcement Learning with Loss Function Weighted by Temporal Difference Error.
%U http://dblp.uni-trier.de/db/conf/icic/icic2023-5.html#ParkKMNH23
%V 14090
%@ 978-981-99-4761-4
@inproceedings{conf/icic/ParkKMNH23,
added-at = {2023-08-08T00:00:00.000+0200},
author = {Park, Bumgeun and Kim, Taeyoung and Moon, Woohyeon and Nengroo, Sarvar Hussain and Har, Dongsoo},
biburl = {https://www.bibsonomy.org/bibtex/2ff1858cdcd18fe1714e57bce63f8442f/dblp},
booktitle = {ICIC (5)},
crossref = {conf/icic/2023-5},
editor = {Huang, De-Shuang and Premaratne, Prashan and Jin, Baohua and Qu, Boyang and Jo, Kang-Hyun and Hussain, Abir},
ee = {https://doi.org/10.1007/978-981-99-4761-4_51},
interhash = {d11fd12e5d7592accdac812ed2049752},
intrahash = {ff1858cdcd18fe1714e57bce63f8442f},
isbn = {978-981-99-4761-4},
keywords = {dblp},
pages = {600-613},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {2024-04-09T18:21:49.000+0200},
title = {Off-Policy Reinforcement Learning with Loss Function Weighted by Temporal Difference Error.},
url = {http://dblp.uni-trier.de/db/conf/icic/icic2023-5.html#ParkKMNH23},
volume = 14090,
year = 2023
}