Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Yunlian Lyu"'
Publikováno v:
Entropy, Vol 25, Iss 4, p 584 (2023)
Recent success stories in reinforcement learning have demonstrated that leveraging structural properties of the underlying environment is key in devising viable methods capable of solving complex tasks. We study off-policy learning in discounted rein
Externí odkaz:
https://doaj.org/article/addf7b4aa4d047c4b2412f00d0ca28b3
Autor:
Yunlian Lyu, Mohammad Sadegh Talebi
Publikováno v:
Neural Processing Letters.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::737c15db3574d88e9b139b64c24cbf68
https://doi.org/10.1007/s11063-023-11190-8
https://doi.org/10.1007/s11063-023-11190-8
Publikováno v:
Neural Processing Letters. 54:3979-3998
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49570d842157eb266e9567eb29a7491c
https://doi.org/10.1007/s11063-022-10796-8
https://doi.org/10.1007/s11063-022-10796-8
Autor:
Lyu, Yunlian1,2 (AUTHOR) yizh@di.ku.dk, Côme, Aymeric3 (AUTHOR) aymeric.come@inria.fr, Zhang, Yijie1 (AUTHOR) m.shahi@di.ku.dk, Talebi, Mohammad Sadegh1 (AUTHOR)
Publikováno v:
Entropy. Apr2023, Vol. 25 Issue 4, p584. 22p.
Autor:
Lyu, Yunlian, Talebi, Mohammad Sadegh
Publikováno v:
Neural Processing Letters; Dec2023, Vol. 55 Issue 7, p9019-9040, 22p
Publikováno v:
Neural Processing Letters; Oct2022, Vol. 54 Issue 5, p3979-3998, 20p