Treffer: Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate.
Title:
Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate.
Authors:
Lin, Yifan1 (AUTHOR) ylin429@gatech.edu, Wang, Yuhao1 (AUTHOR) yuhaowang@gatech.edu, Zhou, Enlu1 (AUTHOR) enlu.zhou@isye.gatech.edu
Source:
Operations Research. Nov/Dec2025, Vol. 73 Issue 6, p3010-3026. 17p.
Database:
Business Source Ultimate
Weitere Informationen
Der Volltext kann Gästen nicht angezeigt werden. Login für vollen Zugriff.