Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Matsuba, Hiroya"'
Meta-reinforcement learning (meta-RL) acquires meta-policies that show good performance for tasks in a wide task distribution. However, conventional meta-RL, which learns meta-policies by randomly sampling tasks, has been reported to show meta-overfi
Externí odkaz:
http://arxiv.org/abs/2203.16801
Publikováno v:
Proceedings of the International Conference on Industrial Engineering & Operations Management; 7/26/2022, p1617-1627, 11p
Publikováno v:
IEOM European Conference Proceedings; 2022, p1617-1627, 11p
Publikováno v:
ACM International Conference Proceeding Series; 1/15/2020, p217-226, 10p
Publikováno v:
ACM International Conference Proceeding Series; 8/5/2019, p1-10, 10p
Autor:
Matsuda, Motohiko, Matsuba, Hiroya, Nonaka, Jorji, Yamamoto, Keiji, Shibata, Hiroshi, Tsukamoto, Toshiyuki
Publikováno v:
ACM International Conference Proceeding Series; 8/5/2019, p1-10, 10p
Publikováno v:
2015 IEEE 8th International Conference on Cloud Computing; 2015, p325-332, 8p
Publikováno v:
2014 IEEE International Conference on Cloud Engineering; 2014, p235-244, 10p
Autor:
Sumimoto, Shinji, Nakashima, Kohta, Naruse, Akira, Kumon, Kouichi, Yasui, Takashi, Kamoshida, Yoshikazu, Matsuba, Hiroya, Hori, Atsushi, Ishikawa, Yutaka
Publikováno v:
Recent Advances in Parallel Virtual Machine & Message Passing Interface (9783642037696); 2009, p9-19, 11p
Publikováno v:
2015 IEEE 8th International Conference on Cloud Computing; 2015, p1159-1166, 8p