Generalized gradient emphasis learning for off-policy evaluation and control with function approximation.

Autor: Cao, Jiaqing1 (AUTHOR), Liu, Quan1 (AUTHOR) quanliu@suda.edu.cn, Wu, Lan1 (AUTHOR), Fu, Qiming2 (AUTHOR), Zhong, Shan3 (AUTHOR)
Zdroj: Neural Computing & Applications. Nov2023, Vol. 35 Issue 32, p23599-23616. 18p.
Databáze: Academic Search Ultimate
Nepřihlášeným uživatelům se plný text nezobrazuje