Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Kujirai, Toshihiro"'
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:
2021 International Symposium on Computer Science and Intelligent Controls (ISCSIC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9fd13986fcd165881c3a8bf1c208fc2f
https://doi.org/10.1109/iscsic54682.2021.00056
https://doi.org/10.1109/iscsic54682.2021.00056
Autor:
Kujirai, Toshihiro, Yokota, Takayoshi
Publikováno v:
SICE Journal of Control, Measurement, and System Integration; May 2019, Vol. 12 Issue: 3 p76-84, 9p
Publikováno v:
Proceedings of SPIE; October 2014, Vol. 9239 Issue: 1 p92390X-92390X-7, 831518p